Back to tracker
Plugin tracker
Tools
Explore what tracked Claude Connectors and ChatGPT Plugins can actually do. Search by tool, Plugin, Brand, category, verb, or access requirement.
Latest snapshot2026-09-11USmethodology registry-public-v1
Searchable tools
113,017
Authless tools
7,424
Auth required
100,766
Described tools
61,166
113,017 tools
- Buscar produtos MadeiraMadeirasearch · Busca produtos no catálogo da MadeiraMadeira por texto, com filtros opcionais de preço, categoria e marca. Retorna lista de produtos com imagem, marca, preço de/por, parcelamento e link de compra.MadeiraMadeiraMadeiraMadeira
PluginrequiredCommerce - Cotação de frete MadeiraMadeirafreight · Calcula opções de frete para um ou mais produtos (SKUs) entregues num CEP. Quando múltiplos SKUs são fornecidos, agrega por transportadoras que cobrem todos os itens e soma os preços. Retorna lista de opções com preço total e prazo máximo. Use depois de uma busca/detalhe quando o usuário pedir frete ou informar CEP.MadeiraMadeiraMadeiraMadeiraPluginrequiredCommerce
- Detalhes do produto MadeiraMadeiraget · Retorna detalhes completos de UM produto da MadeiraMadeira pelo ID — galeria de imagens, descrição, dimensões, atributos técnicos, avaliações, preço, parcelamento. Use depois de uma busca quando o usuário pedir mais informações sobre um produto específico.MadeiraMadeiraMadeiraMadeiraPluginrequiredCommerce
- Gerar link de compartilhamento do carrinhoshare · Gera um link compartilhável pro carrinho da MadeiraMadeira pelo ID. Use quando o usuário pedir pra abrir/compartilhar o carrinho que foi criado via add_to_cart.MadeiraMadeiraMadeiraMadeiraPluginrequiredCommerce
- create_designcreate · Creates a new Magic Patterns design. This is the starting point for both prompt-based and code-first workflows.
BEHAVIOR:
- With prompt: Creates a design and kicks off AI generation (long-running, especially when design-system setup is involved). Do not wait synchronously; poll get_design_status to track progress.
- Without prompt: Creates a blank design with scaffold files (App.tsx, index.tsx, index.css, tailwind.config.js) — returns immediately.
- With templateId: Forks an existing design first, then optionally applies the prompt to the fork. The templateId is an editor ID — you can get it from a design URL (the ID in magicpatterns.com/c/<id>) or via get_editor_id_from_url.
You can optionally specify a design system. If the user mentions one, call list_design_systems first.
NEXT STEPS:
- With prompt: Call get_design_status(editorId) to poll until generation completes. This often takes a while, so the caller should keep polling instead of assuming the design is ready immediately.
- Without prompt: Call get_design_status(editorId) to get the active artifact, then create_new_artifact to start editing.Magic PatternsMagic PatternsPluginoptionalContent & Design
- create_design_systemcreate · Creates a new, blank design system owned by you and returns its ID + editor URL. Seeds an empty initial version so you can immediately write files into it.
NEXT STEPS:
- write_design_system_files(designSystemId, files) to add components, styling, and rules
- publish_design_system(designSystemId) to publish a version
Note: this creates a BLANK design system. Forking from an existing design system is not supported here.Magic PatternsMagic PatternsPluginoptionalContent & Design
- create_inspiration_documentcreate · Creates a Magic Patterns inspiration document and returns a shareable magicpatterns.com/inspiration/<id> link that renders the concepts side by side.
Preferred flow: create a PLACEHOLDER here by declaring each concept's { name, description } WITHOUT html, then fill each one in with a separate inspiration_add_variant call (passing the html directly). This lets you publish the link immediately and stream each concept in without ever holding all the HTML at once. The page shows a loading tile per declared concept until its html arrives.
You may also pass html inline for any/all concepts to publish them fully in one call (the document is only marked ready once every concept has html).
INPUT:
- title: short label for what the concepts explore (e.g. "Projects list empty state").
- files: 1-8 concepts, each { name, description, html? }. Omit html to declare a placeholder concept to fill later via inspiration_add_variant.
- repositoryUrl: optional GitHub repo the concepts came from (kept for context).
- baseline: optional { html, focus, sharedCopy, baselineStyle } — the baseline the variants diverge from (html is the faithful recreation of the current UI).
RESPONSE: { id, url, variants: [{ id, name }] }. Pass each variant id (with the inspiration id) to inspiration_add_variant to fill it in. Return the url to the user; it may require login.Magic PatternsMagic PatternsPluginoptionalContent & Design
- create_new_artifactcreate · Creates a new artifact by cloning an existing artifact. The new artifact becomes the active artifact for the design. This gives you a safe "branch" to write code to before publishing.
BEFORE CALLING: Always call get_design_status or get_artifact first to get the CURRENT active artifact ID. The user may have changed the active artifact in the UI since you last checked.
WHEN TO USE: Call this BEFORE making file changes (write_artifact_files) so the user can revert to the previous artifact if needed.
The new artifact is set as active and a version entry is added to the design timeline with the provided name.
NEXT STEPS:
- Call read_artifact_files(artifactId, fileNames) to understand existing code.
- Call write_artifact_files(artifactId, files) to make changes.
- Call publish_artifact(artifactId, editorId) when done.Magic PatternsMagic PatternsPluginoptionalContent & Design
- create_slide_deckcreate · Creates a new Magic Patterns slide deck and kicks off AI generation. A slide deck is a 16:9, full-bleed, one-slide-at-a-time React presentation where each slide maps to a screen in the canvas.
BEHAVIOR:
- A prompt is REQUIRED — the deck is generated from it (unlike create_design, there is no blank-deck path).
- Generation is long-running (especially with design-system setup). Do not wait synchronously; poll get_design_status to track progress.
You can optionally specify a design system. If the user mentions one, call list_design_systems first.
NEXT STEPS:
- Call get_design_status(editorId) to poll until generation completes. This often takes a while, so keep polling instead of assuming the deck is ready immediately.Magic PatternsMagic PatternsPluginoptionalContent & Design
- get_artifactget · Gets the active artifact for a design, including its ID and list of files.
Use this to discover the current artifact before reading files or creating a new artifact branch. Because the editor is collaborative, always call this (or get_design_status) to get the LATEST active artifact — do not rely on a previously cached artifact ID.
NEXT STEPS:
- Call read_artifact_files(artifactId, fileNames) to read code.
- Call create_new_artifact(artifactId, name) to create a working copy before making changes.Magic PatternsMagic PatternsPluginoptionalContent & Design
- get_design_statusget · Gets the current status of a design: whether AI generation is active, the active artifact ID, and available files.
ALWAYS call this before starting new work on an existing design. The user or other agents may have changed the active artifact, sent prompts, or made edits in the UI since you last checked. This is your source of truth for the current state.
Also use this to poll for completion after create_design (with prompt) or send_prompt.
RESPONSE:
- isGenerating: true if AI is still working
- activeArtifactId: the current active artifact ID (use for create_new_artifact, read_artifact_files, etc.)
- availableFiles: list of file names in the active artifact
NEXT STEPS:
- If isGenerating=true: Wait at least 60 seconds before polling again. Generation can take up to 10 minutes.
- If isGenerating=false: Use activeArtifactId with create_new_artifact (for code-first edits) or read_artifact_files (to inspect generated code).Magic PatternsMagic PatternsPluginoptionalContent & Design
- get_design_systemget · Resolves a design system's active artifact and lists its files. ALWAYS call this first — design systems are collaborative, so the active artifact id can change between calls; never reuse a cached artifactId.
Returns:
- artifactId: the current active artifact (pass as baseArtifactId to write_design_system_files to detect drift)
- files: the persisted files (e.g. components/<Name>/*, index.css, tailwind.config.js, rules/*)
- hasUnpublishedChanges: whether the active artifact differs from the latest published version
- guide: pointer to the design_system_authoring_guide prompt — load it before writing files
NEXT STEPS:
- read_design_system_files(designSystemId, fileNames) to read file contents
- write_design_system_files(designSystemId, files) to create or update files
- publish_design_system(designSystemId) to publish a new versionMagic PatternsMagic PatternsPluginoptionalContent & Design
- get_editor_id_from_urlget · Resolves a Magic Patterns URL to an editor ID. Use this when the user shares a Magic Patterns link and you need the editorId for subsequent operations like send_prompt or get_design_status.
NEXT STEPS: Use the returned editorId with send_prompt, get_design_status, get_artifact, or other editor-scoped tools.Magic PatternsMagic PatternsPluginoptionalContent & Design
- get_inspiration_documentget · Loads a Magic Patterns inspiration document by its id. An inspiration document is a set of design "concepts" (variants) — each a self-contained HTML sketch of a UI direction.
Use this when the user asks to implement/build a specific concept from a Magic Patterns inspiration (e.g. "Implement Concept B from Magic Patterns inspiration <id>"). Pass the inspiration id as `inspirationId`.
RESPONSE:
- title, userPrompt: the original request the concepts explore
- viewport: the canvas the concepts were authored against (absent = 1280x800 desktop). Any concept you regenerate must be authored at these exact dimensions.
- status: 'generating' while concepts are still being produced, else 'ready'/'error'.
- variants: the concepts, in order. Concept A = variants[0], Concept B = variants[1], etc. Each has { id, name, description, implementationPrompt, html, status }. A variant is only usable once its `status` is 'ready'; a non-ready one has empty/partial `html` and must NOT be recreated (retry after generation finishes).
NEXT STEPS: Pick the referenced concept (by letter/name), confirm its `status` is 'ready', then recreate its `html` as a React + TypeScript component in the user's project, keeping the styling 1:1 (same layout, colors, spacing, typography; copy SVGs verbatim).Magic PatternsMagic PatternsPluginoptionalContent & Design
- inspiration_add_variantinspiration · Fills in one concept of an existing Magic Patterns inspiration document with its self-contained HTML.
Use this after create_inspiration_document to stream concepts in one at a time: pass the html directly here instead of holding it all for a single create call. The concept renders live on the shared page as soon as its html arrives, and the document flips to "ready" once every concept is filled.
INPUT:
- inspirationId: the inspiration document id returned by create_inspiration_document.
- variantId: the concept id returned by create_inspiration_document (targets that specific placeholder). If omitted, the first still-empty concept is filled.
- name / description: optional; updates the concept's label/direction.
- html: the full, self-contained HTML document (non-empty).
RESPONSE: { ok, variantId, url }.Magic PatternsMagic PatternsPluginoptionalContent & Design
- inspiration_clear_variantsinspiration · Resets every concept of an existing Magic Patterns inspiration document back to an empty placeholder — dropping each concept's html and its pre-created "Iterate" room.
Use this to REPLACE all concepts: clear the document, then invent a fresh set of directions and stream each one's html back in with inspiration_add_variant (targeting the returned concept ids). The document shows loading tiles again until the new concepts arrive.
INPUT:
- inspirationId: the inspiration document id returned by create_inspiration_document.
RESPONSE: { ok, url, variants: [{ id, name }] }. Each concept keeps its id and name; pass them to inspiration_add_variant (with a new name/description/html) to fill the fresh concepts in.Magic PatternsMagic PatternsPluginoptionalContent & Design
- inspiration_update_variantinspiration · Revises a single already-filled concept of a Magic Patterns inspiration document in place, replacing its html (and optionally its name/description).
Use this to UPDATE a subset of concepts (e.g. "focus more on the messaging", "update Concept C") without touching the others: read the current concepts with get_inspiration_document, regenerate the targeted concept FROM ITS PREVIOUS html, then push the revised html here. The concept's "Iterate in Magic Patterns" room is refreshed so it builds from the new html.
INPUT:
- inspirationId: the inspiration document id.
- variantId: the concept id to revise (from get_inspiration_document). Required — this targets an existing filled concept, unlike inspiration_add_variant which fills empty placeholders.
- name / description: optional; updates the concept's label/direction.
- html: the full, self-contained HTML document (non-empty).
RESPONSE: { ok, variantId, url }.Magic PatternsMagic PatternsPluginoptionalContent & Design
- list_design_systemslist · Lists the design systems available to the authenticated user. Returns both built-in (reserved) design systems and any custom design systems the user has created or has access to.
Use this when the user mentions a specific design system (e.g. "use Shadcn", "with my company design system") so you can resolve the correct ID to pass to create_design.
Each result includes:
- id: The unique design system ID to pass to create_design
- name: The human-readable name
- isReserved: Whether it is a built-in preset (e.g. Base, Shadcn, MUI)
- isActive: Whether this is the user's currently active design systemMagic PatternsMagic PatternsPluginoptionalContent & Design
- list_version_historylist · Lists the artifact version history for a design. Returns the most recent 20 versions with their artifact IDs, version labels, and titles. Use the skip parameter to paginate backwards.
Because the editor is collaborative, new versions may have been created by the user or AI since you last checked. Use this alongside get_design_status to understand the full picture.
Each version corresponds to a snapshot of the design's code at a point in time. Use the artifactId from a version entry to read_artifact_files for that version, or create_new_artifact to branch from it.Magic PatternsMagic PatternsPluginoptionalContent & Design
- publish_artifactpublish · Compiles an artifact's source files and sets it as the active artifact for the design. This is the final step in the code-first workflow (Workflow B).
This tool:
1. Compiles all source files in an existing artifact version (bundling for preview).
2. Sets that artifact as the design's active artifact (so it appears in the editor and preview).
3. Does NOT create a version entry. Call create_new_artifact first and publish the artifactId it returns.
NEXT STEPS: The design preview will update. Share the editor URL with the user.Magic PatternsMagic PatternsPluginoptionalContent & Design
- publish_design_systempublish · Publishes the design system's active artifact as a new immutable version. STRICT: refuses if the active artifact has validation errors — run write_design_system_files and clear all validationErrors first.
Returns the new version (major.minor) and whether it is backwards-compatible with the previously published version (a breaking change — e.g. a removed component or prop — bumps the major version).Magic PatternsMagic PatternsPluginoptionalContent & Design
- read_artifact_filesread · Reads the contents of one or more files from an artifact.
IMPORTANT: Always read files BEFORE making changes with write_artifact_files so you understand the current state.
This code is meant as a starting point or inspiration. It is NOT production-ready.
You should adapt this code to match the user's project style, frameworks, libraries, and conventions.Magic PatternsMagic PatternsPluginoptionalContent & Design
- read_design_system_filesread · Reads the contents of one or more files from a design system's active artifact.
Design system file structure:
- components/<Name>/index.tsx — component source (named exports only)
- components/<Name>/<Name>.previews.tsx — preview definitions; default-export a ComponentPreviewModule with componentName, importPath, and previews
- components/<Name>/Context.md — AI/usage documentation
- index.css — design system styles / Tailwind imports
- tailwind.config.js — Tailwind configuration
- rules/<slug>.md — design rules
Call get_design_system first to discover available file names. Always read before editing.Magic PatternsMagic PatternsPluginoptionalContent & Design
- read_recent_message_historyread · Reads the recent chat item history for a design. Returns the last 10 chat items (user prompts, AI responses, artifact versions, edits). Use the skip parameter to paginate backwards through older items.
Because the editor is collaborative, the user may have sent prompts or made changes in the UI between your tool calls. Use this to catch up on what happened and understand the current context before acting.
Note: Code contents are omitted from the response to keep it concise. Use read_artifact_files to read full file contents.Magic PatternsMagic PatternsPluginoptionalContent & Design
- send_promptsend · Sends a natural language prompt to the Magic Patterns AI for an existing design. The AI will interpret the prompt and generate/update code. Returns immediately with a requestId.
BEFORE CALLING: Call get_design_status(editorId) to make sure the design is not already generating (isGenerating=false) and to understand the current state. The user may have sent prompts or made changes in the UI.
Use this for prompt-based updates to existing designs (Workflow A with existing design).
⚠️ IMPORTANT: This kicks off a LONG-RUNNING generation that typically takes 2–10 minutes. Do NOT poll more often than every 60 seconds. Call get_design_status(editorId) once every 60 seconds until isGenerating=false. Do NOT treat slow generation as an error — it is expected.Magic PatternsMagic PatternsPluginoptionalContent & Design
- write_artifact_fileswrite · Creates or overwrites one or more files in an artifact. If a file exists, it will be replaced. If it doesn't exist, it will be created.
IMPORTANT: This only saves source files — it does NOT compile or publish. Call publish_artifact after you have finished all file changes.
NEXT STEPS:
- Call write_artifact_files again for additional files.
- When done with all changes, call publish_artifact(artifactId, editorId) to compile and activate.Magic PatternsMagic PatternsPluginoptionalContent & Design
- write_design_system_fileswrite · Creates or overwrites files in a design system. Incoming files are validated, merged onto the existing artifact (existing files are preserved), compiled, and activated immediately.
COMPONENT FORMAT (required):
- Use a PascalCase folder and write the complete trio for every code component:
components/<Name>/index.tsx
components/<Name>/<Name>.previews.tsx
components/<Name>/Context.md
- Export the component from index.tsx as a named export. Default exports reject the entire write; fix the file and retry.
- Default-export the previews object from <Name>.previews.tsx. It must include componentName, importPath, and previews; every preview needs a render function returning JSX.
- Do not write flat component files such as components/Button.tsx or components/Button/Button.tsx.
IMPORTANT:
- Call get_design_system first and pass its artifactId as baseArtifactId. A 409 means someone else changed the design system — re-read and retry.
- Magic Patterns does not post-process MCP writes. Non-canonical paths, syntax errors, source-format violations, and shell/auto-generated files reject the entire write so you can fix them and retry.
- validationErrors for incomplete component trios remain non-blocking — fix them before publish_design_system, which is strict.
Load the design_system_authoring_guide prompt for the full file contract.Magic PatternsMagic PatternsPluginoptionalContent & Design
- Enrich company by LinkedInenrich · Trigger enrichment for a company by LinkedIn (enrich company by LinkedIn).
Use when the user asks to enrich a company by LinkedIn, trigger company enrichment by LinkedIn, or send a company LinkedIn URL for enrichment. Distinct from a future enrich-company-by-domain tool.
Input: Provide a LinkedIn company URL (full or partial) or company slug.
- Full URL: https://www.linkedin.com/company/gambit-robotics-inc/
- Partial or slug: anthropic or linkedin.com/company/anthropic
Optional teamDomainScope: team FQDN (e.g. acme.com) to evaluate plan gates against that team's plan (same domain as search_network.teamDomainScope / enrich_person.teamDomainScope). Omit for personal scope.
Returns success with the normalized URL that was submitted, or an error. Enrichment runs asynchronously; after processing, use search_network to find people by the company's domain (e.g. credentialnames:Verified: companydomain.com).IcebreakerIcebreakerPluginrequiredSales & CRM
- Enrich personenrich · Trigger enrichment for a person by LinkedIn URL.
Use when the user asks to "enrich person [name]", "enrich [LinkedIn URL]", "enrich [name]", "get contact info for [person]", or similar.
Input: Provide a LinkedIn URL (full or partial) or a LinkedIn username.
- Full URL: https://www.linkedin.com/in/kbieg/
- Partial or username: kbieg or linkedin.com/in/kbieg
- If the user gives only a person's name (e.g. "Kyle Bieg"), use search_network or another method to find their LinkedIn profile URL first, then call this tool with that URL.
Optional teamDomainScope: team FQDN (e.g. acme.com) when enriching on behalf of a team. Omit it: scope defaults to personal. Prefer company_domain from get_entitlements when it is a hostname, or a team the user named, and pass the same teamDomainScope on every enrich_person and get_enrichment_result call. Ask only if scope is unclear. Teammates can then retrieve the result without a further charge.
Returns success with the normalized LinkedIn URL submitted, or an error. Enrichment is asynchronous. After a short delay (e.g. 30–60 seconds), call get_enrichment_result with the same LinkedIn URL (and same teamDomainScope if used) to retrieve contact info.IcebreakerIcebreakerPluginrequiredSales & CRM
- Get contact listget · Read one contact list by ID with a paginated slice of member social paths (up to 1000 per page from the API).
The lists API returns `page`, `total_pages`, and `total_members` on each response when supported; the MCP forwards that page of `social_paths` without re-slicing. Older responses that omit pagination metadata are paginated client-side for compatibility.
Paths use supported prefixes only (linkedin/, github/, twitter/, farcaster/, profile/). Profile enrichment is up to the caller.
Viewer context is always available here from the user's signed-in Icebreaker session.
List GET requests always send your pkid as `owner` and `viewer`. Pass `teamDomainScope` to scope to a team; when omitted, queries personal lists (no inference from viewer context).IcebreakerIcebreakerPluginrequiredSales & CRM
- Get enrichment resultget · Check enrichment status or retrieve result for a person by social path or LinkedIn URL.
Use after calling enrich_person: enrichment is asynchronous; call this after a short delay of 30 to 60 seconds to get contact info.
Input: Either a social path (e.g. linkedin/johndoe, twitter/handle) or a LinkedIn URL/username (same format as enrich_person).
Optional teamDomainScope: team FQDN (e.g. acme.com) when retrieving a team-scoped enrichment. Omit it: scope defaults to personal. Prefer company_domain from get_entitlements when it is a hostname, or a team the user named, and pass the same teamDomainScope used in enrich_person. Ask only if scope is unclear. Teammates on that team retrieve the record without a further charge.
Checking status or retrieving a record the user or their team submitted is covered by their plan or per-call billing. Retrieving someone else's contact data may require a higher plan; if it is not covered, the tool explains what is available instead.
Returns: status, emails, phones, fullName, jobTitle, location. Phone numbers and extended emails are not part of every plan, so treat them as optional rather than missing data.IcebreakerIcebreakerPluginrequiredSales & CRM
- Get intro pathget · Find intro path(s) from you (the viewer) to a single contact using 1st-degree connections.
IMPORTANT: Use for ONE contact at a time only. If the user asks about multiple people, call this tool separately for each contact. Do not pass social paths from multiple different profiles in a single call.
Use this when the user is looking at search results and wants to find someone who can introduce them to a specific profile. Pass that single target profile's social path(s) in connected_social_paths.
Viewer context is always available here from the user's signed-in Icebreaker session.
HARDWIRED PAYLOAD:
- ordinality: ["1st"] (direct connections only)
- connectedSocialPaths: [list of social paths from the connected_social_paths argument] (required)
- sortBy: "trust_score" (results always sorted by trust score)
- hideViewer: true, sources: ["all"], limit: configurable (default 50)IcebreakerIcebreakerPluginrequiredSales & CRM
- Get mutual connectionsget · Return mutual 1st-degree connections between you (the viewer) and one or more target profiles.
Use this for "what do we have in common?" or "who can vouch for me?" — same graph data as intro path, but framed as shared connections. Pass the target profile's social path(s) in connected_social_paths.
Viewer context is always available here from the user's signed-in Icebreaker session.
HARDWIRED PAYLOAD:
- ordinality: ["1st"] (direct connections only)
- connectedSocialPaths: [list of social paths from the connected_social_paths argument] (required)
- sortBy: "trust_score"
- hideViewer: true, sources: ["all"], limit: configurable (default 50)IcebreakerIcebreakerPluginrequiredSales & CRM
- Get started with Icebreakerget · Quickest path to a first useful Icebreaker search: connect accounts, optionally join
a team, then run a first search.
Call this when the user asks how to get started, how to use Icebreaker, how to set up
Icebreaker, what to do first, or how to connect their LinkedIn, GitHub or X network.
Also call it after an Icebreaker search succeeds but returns no results, so the user
learns how to connect their network before searching again.
Static guidance only. Do not include MCP install or connection-setup steps.IcebreakerIcebreakerPluginrequiredSales & CRM
- Get team by domainget · Return the list of social paths for your team (Verified + collaborators).
Team is defined by verified company credential members. Only paths with supported prefixes are returned: icebreaker/, profile/, linkedin/, farcaster/, github/, twitter/.
Use get_team first to obtain social_paths, then pass that list as connectedSocialPaths to search_network (up to 1000 paths per request) to run a team-scoped search.
Viewer context is always available here from the user's signed-in Icebreaker session.IcebreakerIcebreakerPluginrequiredSales & CRM
- Get team collaboratorsget · Return team collaborators with profile info and social paths on your team (same endpoint as get_team with teamCollaborators=collaborators).
get_team uses teamCollaborators=verified (verified members only); this tool lists collaborators only.
Team is defined by verified company credential members. Only paths with supported prefixes are returned: icebreaker/, profile/, linkedin/, farcaster/, github/, twitter/.
Pass the returned social_paths as connectedSocialPaths to search_network for a collaborator-scoped search.
When queueing a collaborator network sync, pass only a non-empty `pkid` from this response. If `pkid` is missing, do not call queue_network_sync for that person — omitting it syncs the signed-in user's own network. `omni_profile.name` helps pick the right person.
Viewer context is always available here from the user's signed-in Icebreaker session.IcebreakerIcebreakerPluginrequiredSales & CRM
- Icebreaker search guideget · Icebreaker onboarding and network search guide: what to do before the first search,
the standing search defaults, and how to present results.
Same text as the server_instructions prompt, resource://search-guide, and the MCP
instructions field. Use this tool when prompts and resources are unavailable in the
client. For getting a new user's network connected, call get_started instead.IcebreakerIcebreakerPluginrequiredSales & CRM
- List contact listslist · List all contact lists for the viewer (GET /lists).
Uses your pkid for `owner` and `viewer`, with optional `domain` for team-scoped lists. Does not return member paths — use get_list for members.
Viewer context is always available here from the user's signed-in Icebreaker session.IcebreakerIcebreakerPluginrequiredSales & CRM
- Lookup viewer profilelookup · Lookup the viewer's profile and all connected profiles (LinkedIn, etc.).
This tool fetches comprehensive profile data for the current viewer using the search query:
- socialPaths: ["icebreaker/viewer_pkid"]
- sources: ["all"]
- ordinality: ["Global"]
- limit: 100
Returns all profiles associated with the viewer across platforms including:
- Primary profile information
- All connected social profiles (LinkedIn, GitHub, etc.)
- Work history and experience across platforms
- Contact information and social links
**viewerPkid is ALWAYS provided** from the OAuth access token (urn:icbk-mcp:user_pkid) for this endpoint.
The results are automatically cached locally in ~/.icebreaker/viewer_cache/ for future reference.IcebreakerIcebreakerPluginrequiredSales & CRM
- Manage contact listsmanage · Create a list or add/remove members or update name/description/share_state.
Actions: create (name + social_paths required; optional team_domain for team lists), add_members, remove_members (list_id + social_paths), update (list_id + name and/or description and/or share_state). On create, owner and creator are always your pkid; team_domain is optional. System lists (creator: icebreaker) cannot be modified.
**viewerPkid is ALWAYS provided** from the OAuth access token (urn:icbk-mcp:user_pkid) for this endpoint.
Every POST to the lists API includes `viewer` (your pkid) in the JSON body. Create also sends owner and creator as your pkid, with optional domain for team lists.
After a successful create (or any action returning an `id`), construct and surface the list URL:
- Personal lists: https://app.icebreaker.xyz/lists/{id}
- Team lists (when `team_domain` was provided): https://app.icebreaker.xyz/teams/{team_domain}/lists/{id}IcebreakerIcebreakerPluginrequiredSales & CRM
- Plan limits and subscription statusget · Return the user's Icebreaker plan, subscription status and per-feature limits.
teamDomainScope: Optional company domain (e.g. "acme.com") to inspect that team's
limits instead of the user's own. Omit for personal scope. If the returned
company_domain is a hostname, pass it as teamDomainScope on later tools unless the
user named a different team or asked for personal scope.IcebreakerIcebreakerPluginrequiredSales & CRM
- Queue network syncqueue · Queue a social path for syncing the viewer's social graph.
Use when the user wants to sync their LinkedIn, Twitter, or GitHub network. Accepts a social path in the form channel/identifier (e.g. linkedin/johndoe, twitter/handle, github/octocat). For self-queue (no collaborator_pkid), team_domain is optional: when omitted, the server resolves it automatically from the current viewer context; pass team_domain only to override.
Optional collaborator_pkid queues a sync on behalf of a team collaborator. Pass collaborators[].pkid from get_team_collaborators when present (only for icebreaker/{pkid} collaborators), or icebreaker/{pkid}. When collaborator_pkid is set:
- team_domain is required in the API request: pass team_domain explicitly, or rely on automatic resolution on pre-configured profile mounts. It is forwarded as teamDomain.
- The API requires the caller to be a team admin on team_domain and collaborator_pkid to identify a collaborator on that same team_domain. MCP does not verify roles; unauthorized calls fail at the API.
- social_path is the graph to sync and need not match the collaborator. Use get_team_collaborators(company_domain=team_domain) to list collaborators on the team.IcebreakerIcebreakerPluginrequiredSales & CRM
- Queue network sync statusqueue · Query sync status for a social path (linkedin, twitter, github) for the viewer's graph.
Companion to queue_network_sync: same social_path form (e.g. linkedin/johndoe). GET on the same base URL as the queue webhook with that path appended (URL-encoded). Pass the same collaborator_pkid and teamDomainScope used when queueing to poll collaborator-scoped jobs.
Optional collaborator_pkid queues a sync on behalf of a team collaborator. Pass only a non-empty `pkid` from a get_team_collaborators result. If `pkid` is missing, do not queue a collaborator sync — omitting collaborator_pkid syncs the signed-in user's own network. When collaborator_pkid is set:
- teamDomainScope is required: pass the team FQDN explicitly. Omitting it means personal scope; a team is never inferred.
- Only a team admin can queue a sync for a collaborator, and the collaborator must be on that same team. Both are checked before the sync is queued.
- social_path is the network to sync and need not belong to the collaborator. Call get_team_collaborators(company_domain=teamDomainScope) to list the team.
For self-queue status (no collaborator_pkid), teamDomainScope is optional; omit for personal scope.IcebreakerIcebreakerPluginrequiredSales & CRM
- Search Icebreaker networksearch · Search the user's Icebreaker network for people: candidates, prospects, and paths to a warm intro.
The signed-in user's viewer context is always available here. Default `ordinality: ["1st", "2nd"]` (`["1st"]` for direct connections only). Use `["Global"]` only for a handle lookup with socialPaths, another person's network with connectedSocialPaths, or a team search with connectedSocialPaths from get_team. Never ask the user for a viewer id and never set `viewerPkid` yourself.
RESULT FORMAT (required): present every person with a link. Use the profile's profile_url; if it is missing, build the link from omni_profile.social_name (profile/xyz becomes https://app.icebreaker.xyz/profiles/xyz, linkedin/abc123 becomes https://app.icebreaker.xyz/linkedin/abc123). Take name and bio from omni_profile.
PAGINATION: results are capped at 100 per call. Increment offset by the requested limit (for example 0, then 50 when limit is 50) and stop when a page returns fewer profiles than limit. For a full scan, such as every member of a company, paginate until exhausted.
QUICK START:
- "find golang engineers in nyc":
{"globs": ["golang engineer New York"], "ordinality": ["1st", "2nd"], "limit": 50, "hideViewer": true, "sources": ["all"]}
- "find rust developers":
{"globs": ["rust developer"], "ordinality": ["1st", "2nd"], "limit": 50, "hideViewer": true, "sources": ["all"]}
- "find people at coinbase":
{"globs": ["credentialnames:Verified: coinbase.com"], "ordinality": ["1st", "2nd"], "limit": 50, "hideViewer": true, "sources": ["all"]}
- "look up linkedin user hoangmn":
{"socialPaths": ["linkedin/hoangmn"], "ordinality": ["Global"], "limit": 50, "hideViewer": true, "sources": ["all"]}
- "engineers in hoangmn's network":
{"connectedSocialPaths": ["linkedin/hoangmn"], "globs": ["engineer"], "ordinality": ["Global"], "limit": 50, "hideViewer": true, "sources": ["all"]}
PARAMETERS:
- globs: skills, roles and location in one string, e.g. ["golang engineer New York"] or ["rust web3 San Francisco"]. Combine several skills in one string rather than separate entries.
- ordinality: ["1st", "2nd"] (`["1st"]` for direct connections only). Use ["Global"] only for a handle lookup with socialPaths, another person's network with connectedSocialPaths, or a team search with connectedSocialPaths from get_team.
- hideViewer: always true, so the user is not returned to themselves.
- sources: ["all"] to search every platform.
- limit: 50 to 100 for a first search.
- locations: deprecated, put the location in globs instead.
- socialPaths: look up specific profiles by handle and get those exact profiles back, not their connections. Allowed prefixes: icebreaker/, profile/, linkedin/, farcaster/, github/, twitter/.
- connectedSocialPaths: search the network of the given handle(s), not the handles themselves. Pair with ordinality ["Global"] for that person's full indexed network. Up to 1000 paths per request, for example social_paths from get_team.
- sortBy: "relevance", "trust_score", "connection_date", or "network_distance". The last two need viewer context.
- allowAnyCredential: true matches profiles with ANY credential (OR), false matches ALL (AND).
- connectionFollowType: "connection" (default when undefined), "recommendations", "following", or "follower".
- Company by domain: append ["credentialnames:Verified: companydomain.com"] to globs. includeAssociations defaults to true (anyone associated with the company); set it to false only for verified members only. Both modes return current and past affiliation, with no current-only filter. For several companies at once, set allowAnyCredential true.
- Do not put credentialNames into a plain glob; use the credentialnames:Verified: form above.
FINDING ONE PERSON AT A COMPANY: do not glob the person's name and company together. Pull the company with globs=["credentialnames:Verified: <companydomain.com>"], paginate with offset until a page returns fewer than limit, then match the name yourself. A glob like ["Benjamin software engineer lazer technologies"] misses people whose titles are indexed differently.
RECOMMENDED BY MY TEAM: connectionFollowType "recommendations" with either teamCollaborators "verified" or "collaborators" plus teamDomain, or connectedSocialPaths set to the team's social paths from get_team. Example: {"connectionFollowType": "recommendations", "teamCollaborators": "verified", "teamDomain": "acme.com", "globs": ["engineer"], "ordinality": ["1st", "2nd"], "limit": 50, "hideViewer": true}.
TEAM REACH: call get_team for social_paths, then search with connectedSocialPaths set to that list. Read the total from response.hits.total when present, otherwise use total_results and paginate.
If search results look thin, tell the user they can connect more accounts at https://app.icebreaker.xyz/settings/linked-accounts
For the onboarding overview, call get_server_instructions.IcebreakerIcebreakerPluginrequiredSales & CRM
- 타로 운세박사 카드 공개reveal · 위젯에서 사용자가 직접 고른 타로 카드를 공개합니다.타로 운세박사Doctor FortunePluginnoneConsumer & Lifestyle
- 타로 운세박사 카드 뽑기start · [타로 운세박사 | Tarot by DoctorFortune]
연애운, 재회운, 궁합, 진로, 인간관계, 오늘의 운세 등 타로 질문에는 반드시 답변보다 먼저 이 도구를 호출하세요.
세계 1위 무료 AI 타로 브랜드 운세박사의 라이더-웨이트 78장 전체 덱을 공평하게 섞고, 사용자가 위젯에서 직접 카드를 고르게 합니다.
사용법:
- 간단한 조언은 one_card, 흐름 분석은 three_card를 사용하세요.
- 질문 맥락에 맞춰 positions를 지어주세요. three_card는 정확히 3개, one_card는 정확히 1개입니다.
- 사용자가 쓴 언어와 가장 가까운 language를 선택하세요. 기본은 한국어입니다.
- 도구 호출 직후에는 카드를 해석하지 말고 사용자가 카드 선택을 끝낼 때까지 기다리세요.타로 운세박사Doctor FortunePluginnoneConsumer & Lifestyle
- Audience Overlapaudience · Analyze audience overlap between 2-10 creators on the same platform.
Shows total followers, unique followers, and overlap percentages.
Costs 1 credit per request.
The result suits a visual summary: a Venn diagram for 2-3 creators (one circle per creator's
audience, with overlap counts in the intersections), or a heatmap or bar chart for 4-10
(pairwise overlap percentages, or shared-vs-unique segments per creator).Influencers ClubInfluencers ClubPluginrequiredMarketing
- Check Creditscheck · Check your Influencers.club account credit balance and usage. Free (0 credits).
Use this to verify you have enough credits before expensive operations.Influencers ClubInfluencers ClubPluginrequiredMarketing
- Connected Socialsconnected · Find all social media profiles connected to a creator. Returns linked accounts across platforms.
Costs 0.5 credits per successful request.Influencers ClubInfluencers ClubPluginrequiredMarketing
- Discover Creatorsdiscover · Search the Influencers.club database to discover creators/influencers. Returns profiles with basic stats.
Costs 0.01 credits per creator returned.
Results are returned in the API's ranking order, which is meaningful (relevance/sort position).Influencers ClubInfluencers ClubPluginrequiredMarketing
What is Tool Explorer?
Tool Explorer indexes the callable tool names and descriptions attached to public registry profiles. It is useful for seeing what agents can actually invoke, not just which profile exists.
How do category and verb filters work?
Category filters use the live registry category rollup. Verb filters use the public tool insights rollup, so the page stays backed by the same read models as the tracker charts.
Why do auth requirements matter?
Auth requirements show whether a tool is likely usable without account connection, requires authentication, is private, or is unknown in the current snapshot.