Biblos
Allows rendering the knowledge graph as Mermaid diagrams for visualization of document relations.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Biblossave the meeting summary to project Apollo and tag it urgent"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Biblos
Biblos is a multi-agent MCP server that gives your agents a shared, documented memory and a persistent inter-agent message bus. It is not a central brain: every agent keeps its own LLM and local memory. Biblos is the shared library and interconnect that lets otherwise independent agents (e.g. OpenClaw, OpenCode, Claude Code) persist knowledge in one place and hand work to each other in a verifiable way.
Documented memory — every memory is a readable Markdown document plus structured metadata, searchable with keyword (FTS5) ranking.
Inter-agent bus — a persistent request queue with recipient identity verification, so agents can ask each other for work and confirm the outcome.
Implements the Model Context Protocol over Streamable HTTP using the official @modelcontextprotocol/sdk@1.30.0. Persistence is a single SQLite file (better-sqlite3 + FTS5 keyword index). Tested with 116 passing tests (vitest).
Features
Biblos exposes 14 MCP tools across 5 domains.
Domain | Tools | What it does |
Memory documents |
| Store/read/edit/delete Markdown memories with metadata (author, tags, project, type). |
Knowledge graph |
| Add/remove typed relations between documents, traverse the graph by type and depth, and render it as Mermaid (default) or Graphviz. |
Agent registry |
| Explicitly register agent identities (name, type, capabilities). Names are unique; registration is required before an agent can use the bus. |
Inter-agent bus |
| A persistent request queue: send → poll → respond → status. The caller's identity comes from the |
MCP server core | (transport + auth + health) | The stateless Streamable HTTP endpoint, Bearer + Origin auth on every request, and registry/health behavior of the server itself. |
Related MCP server: knowledgeplane
Architecture
Clients (OpenClaw / OpenCode / Claude Code)
│ MCP Streamable HTTP + Bearer + Origin + X-Biblos-Agent
▼
┌─────────────────────────────────────────────────────┐
│ src/index.ts (Node http, stateless, no sessions) │
│ ┌─────────────────────────────────────────────┐ │
│ │ src/auth.ts │ │
│ │ Origin not allowlisted → 403 │ │
│ │ Bearer key mismatch (timing-safe) → 401 │ │
│ └──────────────────┬──────────────────────────┘ │
│ ▼ │
│ McpServer — Streamable HTTP on /mcp (14 tools) │
│ └── domains: documents · graph · bus · registry │
└──────────┬──────────────────────────────────────────┘
│
SQLite (single file)
better-sqlite3
FTS5 + sync triggersDesign principles:
Stateless Streamable HTTP. The server does not use
MCP-Session-Idsessions. Each request is handled by a fresh transport +McpServerinstance, which makes proxying trivial and avoids session-affinity issues.Auth first. Every request passes through
src/auth.tsbefore reaching any tool: anOriginnot inBIBLOS_ALLOWED_ORIGINS(or missing on non-GET) is rejected with 403; a wrongBIBLOS_API_KEYis rejected with 401 (compared withcrypto.timingSafeEqual). The server refuses to start without both variables set.Identity from the header, never from tool arguments. The
X-Biblos-Agentheader fixes the caller's identity at the HTTP boundary, so callers cannot spoof the recipient checks that the bus enforces.No web framework. The Streamable HTTP transport is a single JSON-RPC endpoint, so the native
node:httpserver is enough — no Express/Hono needed, one less dependency surface.
Requirements
Node.js >= 22 (ESM,
NodeNext).No external dependencies. The server is fully self-contained: a single SQLite file is the only state, and search runs entirely on the built-in FTS5 index.
Configuration
All configuration comes from environment variables (see .env.example, read by src/config.ts).
Variable | Default | Purpose |
| — (required) | Bearer API key. The server refuses to start without it. |
| — (required) | Comma-separated Origin allowlist. Requests with a missing/disallowed Origin get 403. |
|
| Drop keyword search hits below this normalized score (0 = keep all). |
|
| SQLite database file path. |
|
| HTTP bind host. |
|
| HTTP bind port. |
Quick start (local)
npm ci
cp .env.example .env
# fill in BIBLOS_API_KEY (e.g. `openssl rand -hex 32`) and BIBLOS_ALLOWED_ORIGINS
npm run build
npm startThe server now listens on http://127.0.0.1:8199/mcp. It starts with zero external dependencies — every tool works with just the SQLite file.
Connecting clients
Biblos speaks MCP Streamable HTTP and requires three things on every request:
Header | Value |
|
|
| one of the |
| the agent's registered name (never in tool arguments) |
See docs/clients.md for step-by-step configuration for OpenClaw (streamable-http transport), OpenCode (type: remote, Bearer header, oauth: false), and Claude Code, plus the registration-first rule and a curl smoke test.
Development
npm run test # vitest run — full suite (116 tests)
npm run typecheck # tsc --noEmit
npm run build # tsc -p tsconfig.build.json + copy src/db/schema.sql → dist/Repository layout:
src/
config.ts env config loader (loadConfig)
index.ts node:http server + stateless Streamable HTTP transport
auth.ts Bearer + Origin middleware (every request)
server/tools.ts 14 MCP tool registrations (zod schemas)
domain/ documents, graph, bus, registry, types
db/ store.ts (better-sqlite3 facade), migrate.ts, schema.sql
tests/ unit, integration, and E2E suites (no external services)
docs/clients.md client integration guide
deploy/ systemd unit, env example, Apache vhost template
openspec/ SDD artifacts (proposal, specs, design, tasks)License
MIT — © 2026 juanvs23.
This server cannot be deployed
Maintenance
Related MCP Connectors
An MCP memory server. One memory your agents share — across models, devices and apps.
- memnodeOAuthdev.memnode
Persistent, inspectable memory for AI agents with lineage, correction, and a hosted MCP endpoint.
Cross-session memory for AI agents with a Source Receipt for every memory, over MCP.
Shared memory for coding agents and their teams: project docs with semantic search, plus epics, tasks, open questions and decisions your agent reads and writes over MCP. Teammates and their agents share the same board. Deploy and permanent delete stay human-only and are enforced by the server. Free tier, no card. Setup: https://app.bilgai.com/docs/connect — API key (blg_) as Bearer or OAuth. Issues: https://github.com/volkansuner/bilg-feedback
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceA production-ready MCP server that enables multiple AI agents to collaborate through a shared, concurrency-safe memory space. It supports advanced search, full CRUD operations, and automatic backups to facilitate asynchronous communication between agents.MIT
- FlicenseNot gradedqualityCmaintenanceMCP 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-
- FlicenseNot gradedqualityAmaintenanceMCP server providing shared working memory for collaborative AI agents, with real-time notes and LLM-consolidated structured memory bank.8-
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to store, search, and resolve shared memories with full provenance, conflict detection, and an audit trail across MCP-compatible clients.MIT