Skip to main content
Glama

@conxt/mcp

Local-first MCP server for governed AI memory. Your agents propose memories; you approve them; only approved memories are ever recalled. Runs standalone with no account — optionally syncs to Conxt cloud for team memory.

Implements the open Governed Memory Record format.

Quickstart

Point your IDE at it — no install, no signup:

Cursor (~/.cursor/mcp.json)

{ "mcpServers": { "conxt": { "command": "npx", "args": ["-y", "@conxt/mcp"] } } }

Claude Code

claude mcp add conxt -- npx -y @conxt/mcp

Claude Desktop → Settings → Developer → Edit Config: same block as Cursor.

That's it. Memory lives in ~/.conxt/memory.json on your machine.

Related MCP server: Centralaizer

The tools

Tool

Who calls it

What it does

remember

agent

Propose a memory (pending — doesn't govern yet)

recall

agent

Recall approved memories for a query

list_pending

agent/you

See what's awaiting approval

approve

you

Approve a pending memory → it now governs

reject / forget

you

Decline or delete

The rule that makes it governed: an agent can propose, but only a human can approve — and recall never returns anything that isn't approved.

Human approval from the terminal

npx @conxt/mcp pending          # what's waiting
npx @conxt/mcp approve <id>     # approve it
npx @conxt/mcp reject <id>
npx @conxt/mcp list
npx @conxt/mcp path             # where the store lives

Prefer zero friction for solo use? Set CONXT_AUTO_APPROVE=1 and everything you remember is approved on the spot.

Cloud mode (optional)

Local is always the source of truth. Set both env vars to also push approved records to your Conxt workspace for shared, governed team memory:

CONXT_API_KEY=...      CONXT_API_URL=https://...

A sync failure never affects your local memory.

Config

Env

Default

Purpose

CONXT_STORE

~/.conxt/memory.json

Local store path

CONXT_AUTO_APPROVE

off

Approve on remember (solo mode)

CONXT_API_KEY / CONXT_API_URL

unset

Optional cloud sync

Develop

npm install && npm run build && node dist/index.js

License

MIT.

Publishing

CI (.github/workflows/ci.yml) builds and runs the governance smoke test on every push. To release to npm:

  1. On npmjs.com, confirm you own the @conxt scope — or rename the package to unscoped conxt-mcp in package.json.

  2. Add an NPM_TOKEN (Automation token) as a repository secret (Settings → Secrets and variables → Actions).

  3. Cut a release:

    npm version patch      # or minor / major — creates a v* tag
    git push --follow-tags

    The publish workflow builds, smoke-tests, and runs npm publish --access public.

Or publish manually:

npm install && npm run build && npm login && npm publish --access public

Available Tools

6 tools
approveA

Approve a pending memory (a human action). Once approved it governs and, if cloud sync is configured, is pushed to Conxt.

Inputs: id (required), approver.

forgetC

Delete a memory by id.

Inputs: id (required).

list_pendingA

List memories awaiting human approval, so they can be reviewed and approved or rejected.

Inputs: limit.

recallA

Recall approved memories relevant to a query. Only human-approved memories are returned — pending or rejected ones never surface.

Inputs: type, limit, query, scope.

rejectB

Reject a pending memory so it never governs.

Inputs: id (required).

rememberA

Propose a new memory. It is recorded as PENDING and does not govern until a human approves it (agents propose, humans approve). Set CONXT_AUTO_APPROVE=1 for frictionless solo use.

Inputs: type (required), content (required), scope, source.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool has a clearly distinct role in the memory lifecycle: remember proposes, recall retrieves approved, list_pending shows pending, approve/reject take opposite actions on pending, and forget deletes. No two tools appear to do the same thing, and the descriptions reinforce their unique purposes.

    Naming Consistency4/5

    All tool names are lowercase verbs, but list_pending uses an underscore while the others are single words (remember, recall, approve, reject, forget). This is a minor deviation but the pattern is still predictable—most are simple imperatives. The inconsistency is small enough to not cause confusion.

    Tool Count5/5

    With 6 tools, the server is well-scoped for a memory management system. It covers the essential operations without redundancy, and the count feels appropriate—not overly thin nor bloated.

    Completeness3/5

    The server covers create (remember), read (recall), and delete (forget) for approved memories, plus approval workflow tools (list_pending, approve, reject). However, there is no update/modify operation for existing memories, and no way to list all approved memories (recall only returns relevant ones). These gaps, particularly the missing update capability, mean the lifecycle is not fully complete.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      A local-first MCP memory server providing persistent, searchable memory for AI agents, powered by SQLite.
      1 npm
      1
      Apache 2.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      A local-first MCP server that gives AI clients a shared, user-owned memory and skills plane, enabling persistent memory across apps via the Model Context Protocol.
      MIT