# MCP Server Documentation - Relex > Relex MCP Server — give your AI agent access to the entire Relex Legal AI API with just two tools (search and execute) in ~1,000 tokens. [Home](/) / [Docs](/docs/a2a) / MCP Server ### Connectors - [All agents](/docs/connectors) - [Claude](/docs/connectors/claude) - [GPT](/docs/connectors/gpt) - [Grok](/docs/connectors/grok) - [Gemini](/docs/connectors/gemini) ### MCP Server - [Overview](/docs/mcp/) - [Quickstart](/docs/mcp/quickstart/) ### A2A Protocol - [Overview](/docs/a2a) #### On this page - [Connect the exact product you use](#clause-2) - [Choose a task, not an API manual](#clause-3) - [Permissions and client approval](#clause-4) - [Verify confidentiality, not just a connection](#clause-5) - [Prove a useful handover](#clause-6) - [Optional decision support with Jev](#clause-7) # Relex MCP Server Connect a compatible assistant to the legal context saved in your Relex workspace. The workspace holds the matter; the authorized assistant reads its permitted context and contributes work. Switching assistants does not automatically import private chat histories. ## Connect the exact product you use Canonical endpoint: `https://relex.legal/api/mcp`. Use the [host-specific setup guides](/docs/connectors) for Claude, ChatGPT, Grok, Gemini Apps or CLI, Perplexity and Harvey. Plans, regions and administrator policies differ. A custom connection is not a reviewed directory listing. Documentation of host support is not a completed Relex interoperability test. Remote connections use Streamable HTTP and OAuth with PKCE S256\. Discovery is at [protected-resource metadata](/.well-known/oauth-protected-resource) and [authorization-server metadata](/.well-known/oauth-authorization-server). The current adapter negotiates `2025-06-18` or `2025-11-25`; it does not advertise the 2026 stateless protocol. Refresh the host's tools after a server update. ## Choose a task, not an API manual | Tool | Purpose and boundary | | ------------------------------ | ------------------------------------------------------------------------------------------------------------------------------ | | list\_matters | Up to 20 authorized matter IDs and links; no matter names or identity fields. | | read\_matter\_context | Read saved, redacted matter context; missing documents remain missing. | | conclude\_matter\_session | Conclude an existing Relex steering session and save its conclusions. Does not import arbitrary chat text or create a session. | | find\_legal\_professionals | Search eligible published profiles by specialty, jurisdiction, language or office country. | | read\_legal\_professional | Read a public profile and current request availability. | | prepare\_professional\_request | Link a matter and professional by ID. Returns a Relex approval route; does not invite, share access or charge money. | These wrappers use the same API validation, account permissions, scopes and PII guards as the generic interface. The live `tools/list` response is authoritative. The existing `search({query, tag?, method?, cursor?})` and `execute({method, path, query?, body?})` remain available. Paths are relative to `/v1`. Use discovery for operations outside the typed workflow. Generic execute may write, delete or contact external services, so its annotations are conservative. Tool-schema and task costs vary; no fixed token footprint or savings is guaranteed. ## Permissions and client approval Start with `relex.cases.read`. Authorize `relex.cases.write` only for needed writes; `relex.draft` is for supported drafting operations. `relex.agent` is broad access, not the default to choose for a read-only workflow. Account and matter authorization still apply inside each API route. Finding a professional is not an engagement or conflict check. Preparing a request does not grant access: the user reviews the recipient and matter in Relex and approves sharing through the native workflow. Do not rely on host confirmation dialogs as the only write-access control. ## Verify confidentiality, not just a connection Identity fields are sealed client-side; encrypted records and protected key material support access from another authorized device. This is not encryption of every matter fact. Redacted text and residual identifying facts can still be sensitive. Browser (default) and custom-endpoint processing have different data paths. Do not paste original identities or documents into an assistant chat as a substitute for the workspace workflow. Read the [verification guide](/guides/verify-legal-ai-privacy), choose processing mode deliberately, and test with synthetic material. Sealed-data calls return safe context/ontology/file workflow guidance rather than disclosing originals. Professional judgment, source review and disclosure obligations remain with users. ## Prove a useful handover Follow the [synthetic matter walkthrough](/guides/portable-legal-context). Check what the first assistant actually saved, then retrieve it in a fresh conversation with a second authorized assistant. An answer left only in a chat is not portable workspace context. Disconnect in the host and revoke the corresponding access under Relex **Settings → API Keys**. Host disconnect alone may leave a credential valid. Test access and refresh denial after revocation. ## Optional decision support with Jev The Jev integration is disabled by default pending privacy and provider validation. When enabled, it can supply typed suggestions alongside tool results. These are advisory, not authorization or legal verification. - When enabled and available, agent turns include `response.jev`. Inspect `decision.next` (`stop`, `ask_user`, `retrieve`, `draft_via_case_agent`, `update_ontology`, `apply_knowhow`, `reconcile_ontology`, or `continue`). - When enabled, ask directly: `POST /jev/decide` with `preset` of `loop`, `route`, `guardrail`, `ontology`, `knowhow`, or `turn`, and a labels-only `state`. - Ontology reads stay summary-first. When enabled, `jev=1` requests an optional top-level `jev` block. Retrieve full context whenever the task needs it, regardless of a suggestion that the summary is sufficient. Jev does not draft and is not legal advice. Never use its suggestions to bypass permissions, source checks or explicit user approval. State and custom questions must contain only de-identified labels, never identities or document bodies. If `jev` is absent, or the direct endpoint returns 503, continue the normal workflow with the same safety checks. No whole-matter token saving is claimed. search({ query: "cases" }) execute({ method: "GET", path: "/onboarding/status" }) // Open a case — never set the tier or name yourself; Relex's eval agent decides // the tier from the matter. Create the case, then drive the eval agent: execute({ method: "POST", path: "/cases", body: {} }) execute({ method: "POST", path: "/agent", body: { type: "eval\_req", caseId: "", payload: { prompt: "" } } }) // The eval agent returns its question or the tier + offer; relay any question, // repeat until it returns the offer, then read the case back with GET /cases?caseId=. See [Quickstart](/docs/mcp/quickstart) for the first calls and troubleshooting. --- _[View this page on relex.legal](https://relex.legal/docs/mcp)_