Meridian
This gives Claude persistent memory across coding sessions so it can pick up where it left off, coordinate multi-step tasks, and queue up items that need human approval before proceeding. Think of it as a stateful layer on top of Claude's otherwise stateless interactions. You'd reach for this when working on longer projects where context retention matters, or when you want explicit human-in-the-loop gates before Claude executes certain operations. It runs over stdio or SSE, so you can integrate it locally or hit the hosted endpoint at usemeridian.us. Solves the "wait, didn't we already discuss this?" problem that crops up in extended AI pair programming sessions.
- tools
- 8
- transport
- STDIO, SSE
- last updated
- Jun 2, 2026
Tools
8 toolsPublic tool metadata for what this MCP can expose to an agent.
start_sessionRegisters a session and loads the sprint with active tasks.
Registers a session and loads the sprint with active tasks.
No parameter schema in public metadata yet.
log_task
No parameter schema in public metadata yet.
claim_taskClaims a task so other sessions skip it.
Claims a task so other sessions skip it.
No parameter schema in public metadata yet.
set_decision
No parameter schema in public metadata yet.
pin_decision
No parameter schema in public metadata yet.
request_hitl
No parameter schema in public metadata yet.
generate_handoff
No parameter schema in public metadata yet.
claim_fileClaims a single class or function in a file so two sessions can edit the same file safely.
Claims a single class or function in a file so two sessions can edit the same file safely.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Meridian
Meridian
Shared, structured project state for long-running AI coding work.
Source-available MCP server for persistent project state — shared task log, pinned decisions, human-in-the-loop queue, and tiered handoffs. Works with Claude Code, Cursor, Cline, Claude Desktop, or any MCP client.
Built-in agent memory (for example Claude Code's CLAUDE.md files and auto memory)
keeps notes as files for that agent. Meridian adds a shared, queryable project
record that several sessions and different MCP clients can read and update. It
works alongside built-in memory rather than replacing it.
Details
- Repository
- github.com/meridianmcp/meridian
- Categories
- AI & LLM Tools, Productivity & Office
- Package
@meridianmcp/mcp- Transport
- STDIO, SSE
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Anchorr Mcpmgthompo1/anchorr-mcpAgent-native CRM. 25 tools — contacts, deals, sequences, enrichment waterfall, audit log.0stars
Mcp Servermiddlebrick/mcp-serverScan APIs for OWASP Top 10, LLM, and GraphQL security vulnerabilities.0stars
Mifactory Logic Verifiermifactory-bot/mifactory-logic-verifierVerify AI agent reasoning and logic for errors and contradictions. Pay-per-use.0starsMifactory Spec Apimifactory-bot/mifactory-spec-apiConvert docs to agent-readable specs with criteria and constraints. $0.10/convert.0stars
Navi X402 Mcpmobileappbyharis/navi-x402-mcpPaid agent tools, zero API keys: crypto, weather, translation, web intel, x402 discovery (USDC/Base)0stars
Alpha (Mossland)mosslandopendevs/alpha-mcpKorean crypto × AI media MCP — channel stance, daily briefs, RAG, canonical store, AI personas.0stars