Everlaw

Search and analyze evidence

Category: Operations
Primary Subcategory: Legal Practice & Matter Platforms

Integration details

Description

Everlaw provides a secure, standardized Model Context Protocol (MCP) server that allows OpenAI to connect to Everlaw and work with live matter data on behalf of an authenticated user. Through the connector, a connected agent can understand a user’s Everlaw project structure, translate natural-language requests into Everlaw search logic, retrieve responsive documents and document text, and analyze metadata and Bates driven result sets. The connected agent can also support natural-language reporting and analysis workflows, while Everlaw remains the governed evidence layer and system of record for case materials, metadata, and work product. Access to Deep Dive via this connector complements search and retrieval tools, as well as Everlaw’s native Deep Dive experience. It is intended to support broader, semantic, evidence-backed questions while preserving Everlaw’s permissions and the integrity of the underlying matter record. The connector is designed to operate within the user’s existing Everlaw permission level. Every request is authenticated and authorized against the user’s Everlaw permissions, so the agent can access only the projects, documents, and data that user is already permitted to view. Deep Dive will also be available through the connector, allowing a user to query Deep Dive over eligible Everlaw project data and retrieve evidence-backed results without changing the underlying matter record. Using the connector, an agent can: Use Deep Dive to ask broader investigative questions and return evidence-backed results, once the Deep Dive tools are available. Convert a natural-language request into a structured Everlaw search. Generate structured reports about project contents, document volumes, custodians, dates, Bates ranges, and other returned data. Search by document text, metadata, Bates or Control number, binder, coding, redactions, productions, processing criteria, and other supported terms. Identify the metadata fields, datasets, and processed uploads available in a project. Retrieve matching documents with Bates numbers, metadata, review links, document-text links, and extracted values. Summarize and analyze retrieved documents or result sets in natural language.

Integration type: Plugin
Verification status: Not applicable
Platform: ChatGPT
Category: Operations
Primary Subcategory: Legal Practice & Matter Platforms
Secondary Subcategories: None listed
Brand: Everlaw
Access: Account required
First tracked: 2026-09-19
Tool count: 11
Geography: US

ChatGPT Plugin Discovery Score

ChatGPT Plugin discovery is coming soon

ChatGPT can surface a Plugin when it matches a user's request.Your Plugin Discovery Score measures how often yours appears.

No spam. Unsubscribe any time.

ChatGPT recommends Airtable when a user asks it to update a CRM. — ChatGPT surfaces Airtable because it matches the user's request.

Primary Subcategory

Competing in ChatGPT Legal Practice & Matter Platforms

View Category

Listed in alphabetical order

Primary Subcategory

AuroraComing soonGet notified

CasepointComing soonGet notified

Casepoint GovComing soonGet notified

Chat JurídicoComing soonGet notified

Courtroom5Coming soonGet notified

EverlawComing soonGet notified

Tools

11 tools agents can invoke

Submit a Deep Dive question to an Everlaw project and return the question id for polling. Deep Dive is a powerful semantic search tool that returns document evidence from a project related to the submitted question.
AskDeepDiveQuestion
Returns the schema documentation and an example for a search query term (e.g. BATES, CONTENTS, LOGICAL).
DescribeProjectSearchTerm
Poll a Deep Dive question and return evidence when it has completed.
GetDeepDiveResponse
List all binders on the given project, including their names, IDs, and owning users. You must have read access on the requested project, or, if the project's database allows org admin access, be an org admin for its owning organization.
GetProjectBinders
List all native datasets in the given project. You must have read access on the requested project, or, if the project's database allows org admin access, be an org admin for its owning organization.
GetProjectDatasets
Return a byte range of a document's original extracted UTF-8 text, given its project and document id. Because document text can be large, it is paginated by byte offset: pass `offset` and `limit` to fetch a slice, then call again with the returned `nextOffset` until `nextOffset` is null. Each slice ends on a UTF-8 character boundary, so a multi-byte character is never split across slices. You must have read access on the requested project, or, if the project's database allows org admin access, be an org admin for its owning organization.
GetDocumentText
List all searchable metadata fields on the given project. This provides project-level searchable Everlaw metadata fields, not database-level semantic or source metadata fields. The list is sorted by field name, and includes the name, the internal ID, and the format. You must have read access on the requested project, or, if the project's database allows org admin access, be an org admin for its owning organization.
GetProjectMetadataFields
List all processed uploads on the given project. You must have read access on the requested project, or, if the project's database allows org admin access, be an org admin for its owning organization.
GetProjectProcessedUploads
Returns a page of documents matching the search id returned from PostProjectSearch, including Bates/Control number, metadata and a presigned URL to download text, sorted by document id. You must have read access on the requested project, or, if the project's database allows org admin access, be an org admin for its owning organization.
GetProjectSearchResult
List all projects you have access to.
GetProjects
Run a search query on a project. This is a 3-stage process. 1. Call DescribeProjectSearchTerm for the term you intend to use to get its query schema and an example. For compound terms (LOGICAL, GROUPING, DEDUPLICATE), also call DescribeProjectSearchTerm for each nested operand's term. 2. Call this tool to execute a search query on the project. A search query is a "term" that identifies the search type, and a "query" with fields specific to that term. The response of this tool contains the number of matching documents, the number of document groups within the matching documents (if using `GROUPING` term), the search id, and any optionally requested extra summary metrics. The search id is essential because it is needed to fetch the search results. 3. Call GetProjectSearchResult with the search id to fetch paginated search results. You must have read access on the requested project, or, if the project's database allows org admin access, be an org admin for its owning organization.
PostProjectSearch

Everlaw FAQ

How do I improve a ChatGPT Plugin's discoverability?

The levers are the listing surface agents actually read: names, descriptions, keywords, tool metadata, and registry health. Which lever matters depends on where discovery breaks, which is what continuous measurement shows.

What are Everlaw alternatives on ChatGPT?

As of 2026-09-21, Everlaw competes with Aurora, Casepoint, Casepoint Gov, Chat Jurídico, Courtroom5, DocketDrafter, GC AI, HighQ, JUNE, LawVu, Mary, May or Shall, Quilia, Relativity, مساعدي — IB Law in ChatGPT Legal Practice & Matter Platforms, ranked by public Discoverability Score.

Where is this profile measured?

This profile uses the geography attached to the latest public registry snapshot: US. Locale tags are intentionally omitted.

Get alerts for Everlaw

ChatGPT Plugin discovery is coming soon

Competing in ChatGPT Legal Practice & Matter Platforms

11 tools agents can invoke