Claude MarketplacesSubmit
xultrax-web avatar

Agent Memory Mcp

xultrax-web/agent-memory-mcp

Markdown files as a shared memory layer across AI tools. Saves rules, decisions, and context with severity levels and enforcement categories, then auto-projects them to AGENTS.md, CLAUDE.md, Cursor MDC files, and Gemini instructions so every tool sees the same constraints. The check_action tool gates destructive operations by matching proposed actions against your rule store and issuing cryptographically signed compliance receipts with 60 second TTLs. Breaking change in v0.12: delete_memory requires a valid receipt. You can grep the memory directory, edit rules in vim, commit to git, and sync across machines. Falls back to regex matching when sampling isn't available, so enforcement works even in clients without LLM-in-the-loop support.

tools
2
transport
STDIO
env vars
3
last updated
Jun 4, 2026
View on GitHub

Tools

2 tools

Public tool metadata for what this MCP can expose to an agent.

writeSave a value to agent memory3 params

Save a value to agent memory

Parameters* required
agentIdstring
keystring
valuestring
readRead a value from agent memory2 params

Read a value from agent memory

Parameters* required
agentIdstring
keystring

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Configuration

AGENT_MEMORY_DIR

Absolute path to a custom memory storage directory. Overrides the default per-project location.

AGENT_MEMORY_SCOPE

Set to 'global' to store memories in ~/.agent-memory/ instead of the per-project default ./.agent-memory/.

AGENT_MEMORY_LOG

Log level: debug | info | warn | error. Defaults to info. Logs go to stderr (won't pollute MCP stdio).

Readme

agent-memory-mcp

Guardrails for AI coding agents — write the rule once, every tool obeys, destructive actions get blocked.

CI License Node MCP

Add to Cursor Install on Smithery

View the full README on GitHub

Details

Repository
github.com/xultrax-web/agent-memory-mcp
Categories
Databases, AI & LLM Tools, Documents & Knowledge
Package
@xultrax-web/agent-memory-mcp
Transport
STDIO
Registry
MCP registry, active

Related Databases MCP servers

View all
1waystation-ai avatarPostgreswaystation-ai/mcpConnect to your PostgreSQL database to query data and schemas.0stars
2hovecapital avatarRead Only Local Postgres Mcp Serverhovecapital/read-only-local-postgres-mcp-serverMCP server for read-only PostgreSQL database queries in Claude Desktop2stars
3cocaxcode avatarDatabase Mcpcocaxcode/database-mcpMCP server for database connectivity. Multi-DB (PostgreSQL, MySQL, SQLite), 19 tools.1stars
4infoinlet-marketplace avatarMcp Mysqlinfoinlet-marketplace/marketplaceRead-only MySQL/MariaDB for AI agents — query, list/describe tables, health. SQL-guarded.0stars
5yash-0620 avatarPostgres Secured (Aegis Zero-Trust)yash-0620/postgres-mcpEnterprise PostgreSQL MCP secured by Aegis Zero-Trust to block unauthorized SQL injections.0stars
6neverinfamous avatarPostgreSQL MCP Serverneverinfamous/postgresql-mcpPostgreSQL MCP server with 203 tools, connection pooling, HTTP/SSE, OAuth 2.1, and tool filtering8stars