mcp-memory-gateway
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
mcp-memory-gateway
A FastAPI + FastMCP shared-memory gateway in front of Honcho v3 — a single shared brain that multiple AI agents read from and write to. It exposes a small, curated, bearer-authenticated surface so every agent can recall context and log changes against one learning memory and stay in sync.
What it does
Endpoints / MCP tools (all bearer-authenticated):
recall(query)— dialectic / similarity recall over the shared representation in Honchoremember(text, agent, tags)— store a durable observationlog_change(summary, agent, area, …)— append a change to the shared, git-versioned ledgerprofile_card()— a compact profile/context card for session primingrecent_changes(n)— the latest entries from the change ledger
The MCP server is mounted at /mcp; equivalent JSON routes are exposed for headless callers (shell scripts, other agent runtimes).
Related MCP server: memex
Design notes
One curated front door over Honcho. The underlying Honcho v3 instance stays untouched and private; this gateway is the only thing agents talk to, which keeps the surface small and auditable.
Two write paths, one source of truth. A change is written to Honcho and appended to a git-versioned Markdown ledger (
EXTERNAL-CHANGES.md), so logging stays reliable even if the memory backend is slow — and the ledger is human-readable history.Auth that is SSE-safe. The
/mcpmount is guarded by a raw-ASGI bearer middleware (notBaseHTTPMiddleware) so it authenticates without buffering the Server-Sent-Events stream.Structured, leak-free logging. Every request emits one compact JSON log line with a request id; payload text and the bearer token are never logged (there are tests that assert this).
Layout
app/— the serviceapp.py— FastAPI + FastMCP app, the 5 tools/routes, and bearer authhoncho_client.py— thin client for a local Honcho v3 instanceledger.py— git-versioned change-ledger writermemory_mirror.py— mirrors recent changes into a delimited block of a memory filestructured_logging.py— JSON request/audit logging with a request-id context var
bin/memory— a smallmemoryCLI for headless callers (recall | card | recent | log)tests/— pytest suite (test_app.py,test_honcho_client.py,test_ledger.py).github/workflows/ci.yml— the CI pipelinerequirements.txt,conftest.py— deps and test config.env.example— the environment variables the service reads
Running it
python -m venv .venv && . .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env # then set MEMORY_GATEWAY_TOKEN
export MEMORY_GATEWAY_TOKEN=...
uvicorn app.app:app --host 127.0.0.1 --port 8910Run the tests:
pip install -r requirements.txt
python -m pytest -qConfiguration
All configuration is via environment variables (see .env.example).
The gateway centers on a single configurable primary peer — the Honcho peer
whose profile card and recall it focuses on (set PRIMARY_PEER, default user).
Point it at whichever identity your agents share context about.
Variable | Purpose | Default |
| Bearer token required on every authed route and on | (required) |
| Base URL of the local Honcho v3 instance |
|
| Honcho workspace id |
|
| Optional bearer for Honcho | (unset) |
| The Honcho peer the gateway centers on (profile card + recall) |
|
| Honcho session holding observations about the primary peer |
|
| Plain-text memory file recent changes are mirrored into |
|
| Directory holding the |
|
What's excluded & why (secrets never enter the repo)
Secrets, virtualenvs, and local runtime data are kept out of the repo by .gitignore and never committed:
.env/*.env(except.env.example) — the bearer token lives only in an environment file (mode0600) on the host and is never committed.venv/,__pycache__/,*.pyc— environment / build artifacts*.log,*.db— runtime logs and local data*.bak*— local backup files
This is a clean, self-contained extract of a larger private deployment: the business-specific modules and the production host details are intentionally not part of this public repo. What remains is the reusable core — the MCP/HTTP gateway, the Honcho client, the ledger, and their tests.
CI
CI runs on every push and pull request and performs:
Secret scan — gitleaks over the full git history
Lint + compile —
ruff checkandcompileallTests —
pytest
License
MIT — see LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Hosted memory for AI agents over MCP. One memory shared by all your agents.
Shared memory for your AI tools: tasks, notes and context every tool can read and write over MCP.
Shared MCP memory for AI agents: knowledge base, skills, todos and agent-to-agent handoffs.
One memory, every AI. A shared, user-owned markdown memory your AI clients read and write over MCP.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceGoverned shared memory platform for AI agents and agent fleets. Provides persistent memory, cross-agent knowledge sharing, permissions, audit trails, and multi-tenant isolation through a Model Context Protocol (MCP) server.4 npm559Apache 2.0
- AlicenseNot gradedqualityCmaintenanceCentralized agentic memory and MCP gateway for LLMs, enabling persistent memory recall, validation, and integration with upstream MCP servers.Apache 2.0
- AlicenseNot gradedqualityDmaintenanceSelf-hosted personal context layer that gives AI agents shared memory via MCP.MIT
- FlicenseAqualityBmaintenanceA stateless MCP server that gives coding agents a curated entry point to shared memory, orchestrating Hindsight (facts) and LightRAG (corpora) for automatic routing, URL ingestion, and consistency tooling.6-