Skip to main content
Glama

ShelbyMCP gives MCP-compatible agents durable memory across sessions. Thoughts live in a local SQLite database with FTS5 search, optional vectors, typed graph edges, project scope, trust fencing, and curated context briefs. The server performs no inference and makes no model API calls.

Quick start

Run the platform-native binary through npm:

npx -y shelbymcp --version
npx -y shelbymcp

The default stdio server stores data at ~/.shelbymcp/memory.db. Existing databases created by ShelbyMCP schema v18 open unchanged.

Package-first integrations are included in the protected v0.4.0 release:

Client

Release package

ChatGPT / Codex

shelbymcp-codex-0.4.0.zip

Claude Code

shelbymcp-claude-code-0.4.0.zip

Cursor and Agent Plugins clients

shelbymcp-agent-plugin-0.4.0.zip

Gemini CLI

shelbymcp-gemini-0.4.0.zip

Antigravity

shelbymcp-antigravity-0.4.0.zip

Claude Desktop

shelbymcp-claude-desktop-<platform>-0.4.0.mcpb

Devin

shelbymcp-devin-0.4.0.zip

Use shelby-mcp setup <client> only when the client package or marketplace entry is not available yet. The fallback supports claude-code, claude-desktop, cursor, codex, gemini, and antigravity; devin directs you to its organization-managed marketplace, while windsurf keeps the legacy local config flow. It safely merges the MCP entry and never appends instructions to a global rules file. See Agent Setup.

Related MCP server: knowledgeplane

What agents can do

The server exposes 12 MCP tools:

  • Capture, search, list, fetch, update, and delete thoughts.

  • Link and traverse typed graph edges with manage_edges, explore_graph, and expand_neighbors.

  • Build trusted, token-bounded context with get_brief and select_context.

  • Audit the database with thought_stats.

Search returns summaries and IDs so clients can fetch full content only when needed. Project-aware operations resolve scope from MCP roots and fail closed when the project cannot be identified. Untrusted or external memories are returned inside explicit data-only fences.

The optional Forage and Onboard skills are packaged with supported clients. They run in the user's agent session; ShelbyMCP does not receive or store model credentials. Standalone prompt bodies remain available:

shelby-mcp forage
shelby-mcp onboard
shelby-mcp migrate
shelby-mcp protocol

HTTP and OAuth

Start Streamable HTTP on port 3100:

SHELBY_API_KEY="replace-with-a-long-random-secret" \
  npx -y shelbymcp --transport http --host 127.0.0.1 --port 3100

Endpoints include /mcp, /health, and MCP discovery documents. Setting SHELBY_API_KEY enables bearer authentication and an OAuth authorization-code flow with protected-resource discovery, S256 PKCE, dynamic client registration, and resource-bound access and refresh tokens. Tokens do not expire or rotate; rotate SHELBY_API_KEY to revoke them. Without it, HTTP runs unauthenticated and the OAuth endpoints return 503; do not bind an unauthenticated server to an untrusted network.

Build from source

git clone https://github.com/Studio-Moser/shelbymcp.git
cd shelbymcp
cargo build -p shelby-mcp
cargo test --workspace
npm ci
npm test

Rust owns the product. Node is used only for the small npm launcher, packaging scripts, and their tests. See Development and Architecture.

Memory-engine pull requests also run a deterministic contract and public retrieval gate. See Memory evaluation.

Reuse in Shelby App

The workspace is intentionally layered for the cross-platform Shelby App:

  • shelby-memory is the SQLite memory engine and all memory-domain behavior.

  • shelby-integrations is the current client catalog plus safe setup/status/uninstall helpers.

  • shelby-mcp exposes the MCP service and reusable Axum router as a library as well as a binary.

The app can embed these crates in-process, share one database contract across macOS and iOS, and host the same HTTP router without spawning Node.

License

MIT. See LICENSE.

A
license - permissive license
Not graded
quality - not tested
B
maintenance

Maintenance

Maintainers
14hResponse time
Release cycle
Releases (12mo)
Commit activity
Issues opened vs closed

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    Not graded
    quality
    A
    maintenance
    Open-source MCP memory server providing persistent, cross-platform context for AI tools via a knowledge graph with encrypted storage.
    18
    13
    AGPL 3.0
  • F
    license
    Not graded
    quality
    C
    maintenance
    MCP server that gives AI agents and teams persistent, shared memory using a knowledge graph with vector embeddings, automatic consolidation of related facts, and hybrid search.
    3
  • A
    license
    Not graded
    quality
    A
    maintenance
    A universal MCP server providing persistent, structured memory through a knowledge graph with graph storage, semantic vector search, and multi-hop traversal for AI agents and IDEs.
    1
    MIT
  • F
    license
    A
    quality
    D
    maintenance
    A lightweight MCP server that provides persistent knowledge graph storage for AI assistants, enabling memory across sessions through entity-relationship storage with JSON file persistence.
    10
    1

View all related MCP servers

Related MCP Connectors

  • Shared, governed long-term memory for AI agents across tools and sessions via MCP and REST.

  • An MCP memory server. One memory your agents share — across models, devices and apps.

  • Your memory, everywhere AI goes. Build knowledge once, access it via MCP anywhere.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Studio-Moser/Shelby-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server