AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
MCP verified MIT Self-run

Archivist MCP

mcp-i3t4an-archivist-mcp · by i3T4AN

Archivist MCP is a local-first memory server for coding agents. It persists decisions, incidents, rules, entities, and graph relationships in SQLite, then exposes them over MCP (stdio/HTTP), SSE team mode, and WebUI. Built for cross-session context continuity, conflict-safe updates, searchable recall, and auditable change history.

↗ Repository
— No reviews yet
0 installs
16 views
0.0% view→install

Install

$ agentstack add mcp-i3t4an-archivist-mcp

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Archivist MCP? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Archivist MCP

Local-first project memory server for agents and developers

[](https://www.python.org) [](https://www.sqlite.org) [](https://modelcontextprotocol.io)

[Features](#features) • [Quick Start](#quick-start) • [MCP Setup](#mcp-setup) • [WebUI](#webui) • [Usage](#usage) • [Tools](#mcp-tools) • [Configuration](#configuration) • [Reliability](#reliability--ops) • [Troubleshooting](#troubleshooting)

Archivist MCP is a memory layer for coding agents. You run it alongside your project, connect your MCP client, and the agent can persist/retrieve decisions, incidents, rules, and architecture context across sessions. WebUI is for human review and controlled write actions when you want visibility before changing memory.

Features

  • Three-tier memory model: working memory, compact core memory (core_memory.md/.json), archival graph
  • Graph + lifecycle safety: typed nodes/edges, state transitions, optimistic concurrency, immutable audit events
  • Hybrid retrieval: FTS + local embeddings + graph degree + recency with provenance and confidence
  • MCP transports: JSON-RPC over STDIO and HTTP (/mcp)
  • Team mode: SSE transport with bearer-token auth, role matrix, and project scoping
  • Controlled write workflows: conflict resolution, branch-to-project promotion, stale-memory invalidation
  • Security hardening: payload allowlists, size/type validation, sanitization, redaction, retention purge
  • Reliability tooling: integrity checks, snapshots, restore, startup recovery, rebuild index+embeddings

Quick Start

Prerequisites

  • Python 3.11+
  • macOS/Linux/Windows

1) Initialize database

python3 scripts/migrate.py --db .archivist/archivist.db

2) Start STDIO server

python3 -m archivist_mcp.stdio_server --db .archivist/archivist.db

3) Seed a project/user (first-time)

python3 - .db --db .archivist/archivist.db

Rebuild derived state

python3 scripts/rebuild_index_and_embeddings.py --db .archivist/archivist.db --project-id proj-1 --root .

Project Structure

archivist_mcp/
  mcp_stdio_server.py      # MCP JSON-RPC over stdio
  mcp_http_server.py       # MCP JSON-RPC over HTTP (/mcp)
  sse_server.py            # Team mode HTTP+SSE
  webui_server.py          # Browser UI + controlled write APIs
  tooling/server.py        # Tool router, validation, envelope/errors
  storage/repository.py    # Graph persistence + lifecycle + audit
  retrieval/               # embeddings + hybrid retrieval
  indexing/                # symbol extraction + incremental indexer
  memory/materializer.py   # core_memory.md + core_memory.json
  migrations/sql/          # schema migrations
scripts/
  migrate.py
  create_snapshot.py
  restore_snapshot.py
  check_integrity.py
  rebuild_index_and_embeddings.py
tests/
  test suites for integration, retrieval, security, team mode, and WebUI behavior
docs/
  quickstart.md
  troubleshooting.md
  recovery_runbook.md

Troubleshooting

AUTHZ_DENIED

Token role/scope does not permit the tool or project. Check ARCHIVIST_SSE_TOKENS role and projects.

CONFLICT_ERROR

Optimistic version mismatch. Re-read node, use latest version, retry or resolve via conflict workflow.

EMBEDDING_DISABLED

Embeddings are disabled/unavailable. Retrieval falls back to fts_graph mode.

Blank WebUI timelines

The UI reads from the DB passed to webui_server --db. Ensure your seeding and servers all point at the same DB path.

Documentation

  • Quickstart: [docs/quickstart.md](docs/quickstart.md)
  • Troubleshooting: [docs/troubleshooting.md](docs/troubleshooting.md)
  • Upgrade/Migration: [docs/upgrademigration.md](docs/upgrademigration.md)
  • Recovery runbook: [docs/recoveryrunbook.md](docs/recoveryrunbook.md)
  • Security threat model: [docs/securitythreatmodel.md](docs/securitythreatmodel.md)

Built for durable project memory across agent sessions, with local-first defaults and auditable writes.

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Databases