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
- List Projectsmittwald · List all projects that you have access to.mittwaldmittwald
PluginrequiredDeveloper Tools - List Redis Databasesmittwald · List Redis databases for a project.mittwaldmittwaldPluginrequiredDeveloper Tools
- List Redis Versionsmittwald · List available Redis versions.mittwaldmittwaldPluginrequiredDeveloper Tools
- List Registriesmittwald · List registries available in Mittwald.mittwaldmittwaldPluginrequiredDeveloper Tools
- List SSH Usersmittwald · List all SSH users for a project.mittwaldmittwaldPluginrequiredDeveloper Tools
- List SSL Certificatesmittwald · List SSL/TLS certificates available for a domain.mittwaldmittwaldPluginrequiredDeveloper Tools
- List Serversmittwald · List servers for an organization or user.. Shows all servers accessible to the current user.mittwaldmittwaldPluginrequiredDeveloper Tools
- List Stack Servicesmittwald · List all services within a given stack.mittwaldmittwaldPluginrequiredDeveloper Tools
- List Stacksmittwald · List stacks for a given project.mittwaldmittwaldPluginrequiredDeveloper Tools
- List Virtual Hostsmittwald · List domain virtualhosts.mittwaldmittwaldPluginrequiredDeveloper Tools
- List Volumesmittwald · List persistent volumes that belong to a project stack.mittwaldmittwaldPluginrequiredDeveloper Tools
- Request SSL Certificatemittwald · Request a new SSL/TLS certificate for a domain using Let's Encrypt.mittwaldmittwaldPluginrequiredDeveloper Tools
- Restart Containermittwald · Restart a container.mittwaldmittwaldPluginrequiredDeveloper Tools
- Revoke API Tokenmittwald · Revoke an API token.. Permanently disables the specified API token.mittwaldmittwaldPluginrequiredDeveloper Tools
- Revoke Organization Invitemittwald · Revoke an invite to an organization.mittwaldmittwaldPluginrequiredDeveloper Tools
- Revoke Organization Membershipmittwald · Revoke a user's membership to an organization.mittwaldmittwaldPluginrequiredDeveloper Tools
- Start Containermittwald · Start a stopped container.mittwaldmittwaldPluginrequiredDeveloper Tools
- Stop Containermittwald · Stop a running container.mittwaldmittwaldPluginrequiredDeveloper Tools
- Uninstall Appmittwald · Uninstall an app.mittwaldmittwaldPluginrequiredDeveloper Tools
- Update App Propertiesmittwald · Update properties of an app installation. (use upgrade to update the app version)mittwaldmittwaldPluginrequiredDeveloper Tools
- Update Backup Schedulemittwald · Update a backup schedule.mittwaldmittwaldPluginrequiredDeveloper Tools
- Update Cron Jobmittwald · Update a cronjob.mittwaldmittwaldPluginrequiredDeveloper Tools
- Update DNS Zone Recordsmittwald · Update DNS zone records..mittwaldmittwaldPluginrequiredDeveloper Tools
- Update Delivery Boxmittwald · Update a delivery box.mittwaldmittwaldPluginrequiredDeveloper Tools
- Update Mail Addressmittwald · Update a mail address.mittwaldmittwaldPluginrequiredDeveloper Tools
- Update MySQL Usermittwald · Update properties of an existing MySQL user.mittwaldmittwaldPluginrequiredDeveloper Tools
- Update Projectmittwald · Update an existing project.mittwaldmittwaldPluginrequiredDeveloper Tools
- Update Registrymittwald · Update an existing registry in Mittwald.mittwaldmittwaldPluginrequiredDeveloper Tools
- Update SSH Usermittwald · Update an existing SSH user.mittwaldmittwaldPluginrequiredDeveloper Tools
- Upgrade App Versionmittwald · Upgrade app installation to target version.mittwaldmittwaldPluginrequiredDeveloper Tools
- View Container Logsmittwald · Display logs of a specific container. Use mittwald_container_list to find the containerId for your container.mittwaldmittwaldPluginrequiredDeveloper Tools
- Cancel a running workflowcancel · Cancel an in-flight CodeWords workflow run.
Args:
request_id: id of a running workflow run (from
`run_workflow` with run_async=True).
Constraints:
- Only running runs can be cancelled. Already-completed runs return
a 404-mapped failure response.
- Cancellation is best-effort: the run is signalled to stop and will
terminate when it next reaches a cancellable state.
- The caller must have permission to cancel the run (i.e. it must be
the user's run, or a run on a service the user owns).
Returns: `{success, request_id, message, details?}`.CodeWordsCodeWordsPluginrequiredAI
- Check workflow code for errorsvalidate · Validate a CodeWords service file before deploying it.
Args:
file_url: a `file_url` returned by `edit_service`. The service code
is downloaded and checked.
Validation covers Python syntax and imports, the PEP 723 metadata
header, FastAPI app structure, Pydantic models and type hints,
declared dependencies, environment-variable declarations, and
CodeWords best-practice compliance.
Returns: validator output including `all_passed` and a per-check
report.CodeWordsCodeWordsPluginrequiredAI
- Deploy a workflowdeploy · Deploy a CodeWords service to the user's account.
Args:
file_url: file_url returned by `edit_service`.
service_name: human-readable name for the service.
service_id: optional. Provide an existing id to publish a new
implementation of the same service; omit to create a
new service (a uuid-suffixed id is generated).
description: optional short description; if omitted, one is derived
from the code's docstrings.
visibility:
- "private": only the owner can run the service.
- "public": anyone with the service id can run it; source is
not readable by others.
- "template": same as "public" for execution, plus the source is
readable and clonable. Note: visibility="template"
does NOT promote a service into the public template
gallery — that catalog is curated separately.
change_summary: required, 3-6 words describing what changed in
this version (e.g. "Added retry on 429"). Cannot
be a generic word like "deployed".
Returns: deployment outcome including `success`, `service_id`,
`implementation_id`, `applied_visibility`, and a `warning` if the
applied visibility differs from what was requested. Stable mode may
also return `outcome` and `artifact_digest`.CodeWordsCodeWordsPluginrequiredAI
- Edit workflow source codeedit · Edit a CodeWords service file by applying a sequence of string
replacements, then upload the result to a stable URL.
Sources:
- First call: pass a starting source — "workflow_skeleton" for the empty
template, a CodeWords template id (e.g. "youtube_to_mp3"), or a
service id the caller owns.
- Subsequent calls: pass the `file_url` returned by a previous edit.
Args:
source: starting point or previous edit's file_url (see above).
description: short summary of this edit batch (required, free text).
edits: list of {old_str, new_str, replace_all} ops applied
sequentially and atomically — either all succeed or none.
`old_str` must be unique unless `replace_all=True`. Matching
falls back through whitespace-insensitive, indent-flexible,
and fuzzy strategies.
target_filename: optional, first call only; defaults to a name
derived from the source.
return_content: if True, the response includes the post-edit file
contents with line numbers. Defaults to False (a
file_url is returned for download instead).
Returns: `{file_url, filename, num_edits, message}`. If any edit
matched non-exactly, `match_info` and `match_details` describe the
strategy used and a unified diff so the caller can verify.CodeWordsCodeWordsPluginrequiredAI
- Get output of a workflow runget · Get the final output of an asynchronous CodeWords workflow run.
If the run is still in progress, this call long-polls until the run
completes or until `timeout_seconds` elapses.
Args:
request_id: the id returned by `run_workflow` (run_async=True).
timeout_seconds: maximum poll duration, 1-3600 (default 300).
Returns: `{request_id, output, status, error?}`. On timeout, raises
408. Large outputs are auto-uploaded to a file URL with a preview
included in `output.message`.CodeWordsCodeWordsPluginrequiredAI
- List recent workflow runsget · List recent runs of one of the user's CodeWords services.
Args:
service_id: id of the service whose run history to fetch.
limit: number of most-recent runs to return (1-100, default 10).
Returns: `{success, service_id, service_name, total_requests,
requests: [...]}`. Each request entry includes `id`, timestamps,
HTTP status, request URL, and a snapshot of input/output if
available.
Use the returned `id` with `get_workflow_logs` for detailed log
output of a specific run.CodeWordsCodeWordsPluginrequiredAI
- List the user's stored secretslist · List the names and metadata of secrets the current user has stored
on CodeWords. Secret values are never returned by this tool.
Args:
service_id: optional. Scope listing to include per-service overrides.
Returns: {success, count, secret_names, secrets}.CodeWordsCodeWordsPluginrequiredAI
- List the user's workflowslist · List the services owned by the current CodeWords user.
Args:
include_deleted: include soft-deleted services. Defaults to False.
limit: max services to return, 1-100 (default 50).
visibility_filter: "all" | "public" | "private" | "template".
Returns: `{success, total_services, services: [{id, name,
description, visibility, has_active_implementation, created_at,
updated_at, tags, is_deleted}]}`.CodeWordsCodeWordsPluginrequiredAI
- List versions of a workflowlist · List the saved implementations (versions) of a CodeWords service the
user owns, including which one is currently active.
Args:
service_id: id of the service.
Returns: `{success, service_id, service_name,
active_implementation_id, total_implementations,
implementations: [{id, created_at, change_summary, …}]}`. The
returned `implementations` are ordered most-recent-first.CodeWordsCodeWordsPluginrequiredAI
- Read CodeWords platform guidesconsult · Read one or more CodeWords platform reference documents. The corpus is
written for an LLM agent that is helping a user build, run, and maintain
CodeWords workflows: it covers platform concepts, integration playbooks,
service-structure rules, and template source code. All paths are
relative to the docs root.
Batching saves round-trips, but the assembled response is capped: if the
docs you request total more than ~40,000 characters, the largest one is
replaced by a file link instead of its content. Each doc's size is shown
in brackets in the system-prompt catalog — keep a batch under that, and
fetch a heavy doc (a mode guide, an API reference) on its own.
Args:
paths: Array of relative doc paths (e.g. ["README.md",
"01-core-practices/01-introduction.md"]). Defaults to ["README.md"]
which returns the table of contents.
Returns: a `documents` map keyed by path with `{ content, success }`, plus
a `summary` block with totals and the list of paths that failed.CodeWordsCodeWordsPluginrequiredAI
- Read logs for a workflow runget · Fetch logs for a single CodeWords workflow run, identified by
request_id.
Args:
request_id: the id returned by `run_workflow` (run_async=True),
`cancel_workflow`, or `get_workflow_requests`.
follow: if True, stream logs until the run completes; if False,
return the logs available right now (or up to a 30-second
cap). Defaults to True.
max_entries: cap on returned entries (1-10000, default 1000).
**When to use this tool:**
- To monitor progress of an async workflow execution
- To debug issues with a workflow run
- To get detailed execution information
- To track long-running workflows in real-time
**Cost-aware polling pattern (PREFERRED for long runs):**
Each call re-sends the full set of log entries into chat context unless
you pass `since_timestamp`. To avoid re-paying for entries you've
already seen, capture `last_timestamp` from each response and pass it
as `since_timestamp` on the next call.
# initial fetch
r1 = get_workflow_logs(request_id="cwr-…", follow=False)
# later, only NEW entries:
r2 = get_workflow_logs(
request_id="cwr-…", follow=False,
since_timestamp=r1["last_timestamp"],
)
For quick "did anything happen?" checks, use `head_only=True` which
returns just metadata (no log bodies).
Returns: `{request_id, logs: [{timestamp, level, message, metadata?}],
total_entries, is_complete, last_timestamp}`. `is_complete=False`
indicates the cap or the time-limit was reached before the run finished;
`last_timestamp` is the cursor for incremental polling.CodeWordsCodeWordsPluginrequiredAI
- Run a code snippet in a CodeWords sandboxrun · Run a snippet of Python in an isolated CodeWords sandbox (E2B). The
sandbox is created per call, has no persistent filesystem, and is
destroyed when the call returns. The same runtime is used by deployed
CodeWords services, so behaviour matches production.
Args:
code: Python source to execute. Required for a new run; omit when
reconnecting via `execution_id`.
execution_id: ID returned by a previous call when status was
"running". Used to reconnect to a still-running
process and stream new output. Format
"sandbox_id:process_id[:stdout_offset:stderr_offset]".
dependencies: PyPI packages to install in the sandbox, with pinned
versions, e.g. ["httpx==0.28.1"]. The CodeWords client
("codewords-client==0.4.6") is always included.
secrets: names of the user's stored secrets to inject as environment
variables in the sandbox. The secrets must already exist;
values are injected server-side and must never be printed.
max_execution_minutes: total runtime budget for the sandbox, 1-60.
If a run exceeds ~4.5 minutes, the call returns with status="running"
and an `execution_id`. Subsequent calls with that id return only new
stdout/stderr since the previous offset, until the run completes or
hits `max_execution_minutes`.
Returns: `{success, exit_code, stdout, stderr, execution_time,
dependencies, secrets_loaded}` on completion, or
`{status:"running", execution_id, partial_stdout?, partial_stderr?,
elapsed_seconds, remaining_minutes}` while still running.
The sandbox runs as your CodeWords account and uses your CodeWords
credits.CodeWordsCodeWordsPluginrequiredAI
- Run one of the user's CodeWords workflowsrun · Execute one of the user's CodeWords workflows on the CodeWords
runtime API (runtime.codewords.ai). The workflow must be a service
the current user owns or a published CodeWords platform service.
Args:
workflow_id: the service id of the workflow to run.
inputs: dict of parameters required by the workflow. The shape is
defined by the workflow's input schema; resolve it via
`view_service_code` or `consult_docs` on the matching
template README before calling.
path: optional sub-path on the workflow (e.g. "check-connection/
{app_slug}"). Defaults to the workflow's main entrypoint.
method: HTTP method (default "POST"). Use "GET" for read-only
endpoints such as discovery and connection checks.
run_async: if False (default), waits up to `timeout_seconds` and
returns the output. If True, returns immediately with a
`request_id` for retrieval via `get_workflow_logs` /
`get_workflow_output`.
timeout_seconds: sync-mode wait, 1-3600 (default 300).
is_template: True if the target service is a CodeWords platform
template rather than an owned service.
debug: when True, sets LOGLEVEL=DEBUG on the workflow run.
Constraints:
- The synchronous path enforces a ~5 minute client timeout. If the
workflow takes longer the connection drops, but the run continues
on the sandbox and is billed until completion or until the
platform's 30-minute cap. For long-running workflows use
`run_async=True` and poll with `get_workflow_output`.
Returns:
- Sync: `{output, logs, request_id, status, duration_seconds}`.
- Async: `{output: null, logs: null, request_id, status:"started",
message}`.CodeWordsCodeWordsPluginrequiredAI
- Search CodeWords workflow templatessearch · Search the CodeWords workflow-template catalog.
Supports two modes:
- Semantic (preferred): pass `query` with a natural-language description.
Uses vector similarity to find matching templates.
- Tag-based: pass `tags` with one or more tags to match. Matching is
case-insensitive and supports both exact and substring match
(e.g. "llm" matches "llm-integration"). `match_mode` controls
OR ("any") vs AND ("all") logic.
Returns: a `results` array of `{id, title, description, tags,
matched_tags, match_types}` and a `summary` with `total_results`,
`search_tags`, `match_mode`, and `all_available_tags`.CodeWordsCodeWordsPluginrequiredAI
- Switch active version of a workflowset · Switch which implementation of a CodeWords service the user owns is
the active one. All future requests against the service use the new
active implementation immediately.
Args:
service_id: id of the service.
implementation_id: id of an existing implementation of that
service (see `list_service_implementations`).
Returns: `{success, service_id, service_name,
previous_active_implementation_id, new_active_implementation_id}`.CodeWordsCodeWordsPluginrequiredAI
- Track a task listtodo · Track a task list for the current session. Pass the full updated list
each call (the server does not retain state between calls); the
response echoes the list back along with status counts so the client
can render it.
Args:
todos: full list of task items. Each item has `content` (the task
description), `status` ("pending" | "in_progress" |
"completed"), and optional `substeps` (recursive todo items).
Returns: `{message, status_summary: {pending, in_progress,
completed}, todos: [...]}`.CodeWordsCodeWordsPluginrequiredAI
- View workflow source codeview · Read the source of a CodeWords service.
Args:
source: either a CodeWords service id (deployed service the user
owns or a public template) or a file URL such as one
returned by `edit_service`. The special string
"workflow_skeleton" returns the empty service template.
implementation_id: optional. With a service id, fetch a specific
historical implementation rather than the
active one. Ignored when `source` is a URL.
show_line_numbers: if True, the returned `service_code` is
prefixed with line numbers (and `total_lines`
is included).
Returns: `{success, source, source_type, service_code, ...}`. For
service-id sources, also includes `service_id`, `service_name`,
`implementation_id`, `is_active_implementation`, `owner_id`,
`is_template`, `code_length`.CodeWordsCodeWordsPluginrequiredAI
- Checkpoint Createcheckpoint · Create a new checkpoint of the current sprite state. Returns streaming NDJSON progress.SpritesFly.ioPluginrequiredDeveloper Tools
- Checkpoint Getcheckpoint · Get details of a specific checkpoint.SpritesFly.ioPluginrequiredDeveloper Tools
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.