LangChain connects to Provely through the MCP server, the CLI, the SDK, the REST API. The agent does the action. Provely verifies the outcome and signs a receipt. LangChain never holds the verifier credentials.

A person verified the LangChain capabilities on 2026-10-10. Agent products change monthly. Re-verify before you build.

Source: integration profile langchain · retrieved 2026-10-10

Which surfaces does LangChain use?

SurfaceSupportDetail
MCP serverSupportedtransport stdio, http
CLISupportedRuns through the shell tool of the agent.
SDKSupportedlanguages python, typescript; adapter langchain
REST APISupportedAny HTTP call reaches the control plane.

Which guidance files does LangChain read?

Provely ships one Agent Skill for this host, so the agent knows to verify an outcome before it claims done. The renderer writes prompt fragment from one source. A new agent needs a profile, not core code.

Explain: each file, its path and its write mode
FormatPathMode
prompt fragmentprovely/prompt-fragment.mdfragment
CI gate workflow.provely/ci/github-actions.ymlfragment

How is a false completion claim blocked?

Guidance asks. A hook and the CI gate enforce. A host with neither still receives the verdict, and a person reads it before the work ships.

Explain: what each control does on this host
EnforcementSupportDetail
Advisory guidanceSupportedThe instruction files state the rules for every agent.
Lifecycle hooksSupportedwrap_tool_call
CI gateSupportedprovely verify --wait fails the pipeline unless the verdict is VERIFIED.

How do I connect LangChain?

Connect LangChain to Provely

  1. Install the CLI.Run npx provely --version, or download the static binary.
  2. Register the MCP server.Add the Provely server. Use provely mcp for stdio, or the hosted HTTP server with a bearer token. The tools are begin, verify, status, and receipt.
  3. Write the guidance files.Run provely init --agent langchain. It writes provely/prompt-fragment.md (fragment), .provely/ci/github-actions.yml (fragment). The guidance carries one rule: a successful tool call is not completion.
  4. Install the hooks.Enable the wrap_tool_call hooks. A hook calls the CLI and blocks a completion claim while an operation is PENDING.
  5. Add the CI gate.Run provely verify --wait <duration> in the pipeline. The step fails unless the verdict is VERIFIED. Exit codes: 0 VERIFIED, 2 PENDING, 3 FAILED, 4 CONTRADICTED, 5 UNVERIFIABLE, 1 error.
  6. Report the verdict exactly as returned.VERIFIED: "The action is verified complete. Receipt: <id>." PENDING: "The action is accepted but not yet verified. Operation: <id>."

What else does the profile state?

  • Verified 2026-10-10: this repository ships the interception point. provelyMiddleware goes through createMiddleware of the langchain package, and then to createAgent. Source: examples/typescript/langchain/main.ts.
  • The middleware uses wrap_tool_call, which can stop a tool call before it runs. before_model, after_model, before_agent, and after_agent cannot. Source: https://docs.langchain.com/oss/python/langchain/middleware/custom.
  • The interception point is code, not a script. It blocks only after the application passes the middleware to createAgent. An application that never passes it gets advisory guidance and the CI gate.
  • A LangChain 1.x agent runs on @langchain/langgraph. A project that builds the graph itself with StateGraph or createReactAgent renders the langgraph profile.

LangChain keeps its action credentials, and no surface returns the verifier credentials to it. Read the credential boundary. An operation outlives the session that opened it. Read the API reference.

Which host versions does the profile cover?

>=1.0.0. The integrations team last verified the profile with langchain 1.5.10 and @langchain/core 1.2.9 on 2026-10-10.