MCP.Market

Repomemory MCP server

by DanielGuru·io.github.DanielGuru/repomemory·v1.3.0·2 stars
No reviews yet

Persistent memory for AI coding agents. Hybrid search, auto-session capture, context routing.

B82/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
New

2 stars101 downloads/wk

Reviews

Write one

Nobody has reviewed Repomemory yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Repomemory tools (7, 2 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • context_auto_orient

    Get a comprehensive project orientation in a single call. Returns the project index, recent session summaries, and recently modified entries. Use this at the START of every new coding session to immediately understand the project. This replaces the need to make 3-4 separate tool calls.

  • context_deletewrite action

    Delete a knowledge entry from the repository context. Use this to remove stale or incorrect information. Knowledge quality matters more than quantity \u2014 prune aggressively.

  • context_list

    List all knowledge entries in the repository context, optionally filtered by category. Returns filenames, titles, and age for browsing. Use this to understand what knowledge already exists before writing new entries.

  • context_read

    Read the full content of a specific context file. Use after context_search or context_list to get complete details.

  • context_search

    Search the repository's persistent knowledge base. Returns relevant facts, decisions, regressions, and session notes. Use this FIRST at the start of every task to find relevant context, or when you need to understand why something is the way it is. This prevents re-discovering architecture and re-debating past decisions.

  • context_writewrite action

    Write a new piece of knowledge to the repository's persistent memory. Use this to record: discoveries you made during this session, architectural decisions, bug patterns, or any insight that would help a future AI session. This persists across sessions \u2014 write anything you'd want a future version of yourself to know.

  • summary

    What you worked on and any discoveries worth remembering

Public scan report

scanner v0.1.10 · 2026-09-28 · same rubric, same numbers if you re-run it

no findings
  • Code scan45 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 166 days ago8/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Repomemory compares

Against every graded Web search MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
82/100
higher than 68% of 3,470 Web search servers
Tools
7
the typical Web search server has 5
Tools that change things
29%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
2
more than 70% of 1,786 Web search servers
Downloads a week
101
more than 57% of 827 Web search servers with a package

What its tools let an agent do: 5 read · 2 change

Install Repomemory in Claude Code, Cursor or VS Code

Runs npx -y repomemory on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add repomemory -- npx -y repomemory
Add to Cursor

What the publisher says

From the Repomemory repository's README, as published. We do not edit it. Read it on GitHub

repomemory

Your codebase never forgets.

AI agents lose context every session. repomemory fixes that — one command creates a persistent, searchable knowledge base that any AI tool can read, search, and write to.

npx repomemory go

The Problem

Every time you open a project with Claude Code, Cursor, Copilot, or any AI coding agent:

  • It re-discovers your architecture from scratch
  • It proposes changes that were already debated and rejected
  • It re-introduces bugs that were already fixed

Your CLAUDE.md / .cursorrules helps, but it's static and gets stale.

The Solution

.context/
├── index.md              ← Quick orientation (loaded every session)
├── facts/                ← Architecture, database, deployment
├── decisions/            ← "We chose Drizzle over Prisma because..."
├── regressions/          ← "This broke before. Here's what happened."
├── preferences/          ← Your coding style — follows you across all repos
├── sessions/             ← Auto-captured AI session summaries
└── changelog/            ← Monthly git history syncs

Facts tell agents how things work. Decisions prevent re-debating. Regressions prevent re-breaking. Preferences teach agents how you code.

Quick Start

With an API key (Claude Code, terminal workflows)

npx repomemory go

One command: sets up global profile, creates .context/, configures Claude Code + Cursor, runs AI analysis, prints CLAUDE.md instructions.

With Cursor (no API key needed)

npx repomemory setup cursor

This installs everything Cursor needs:

  • MCP server in ~/.cursor/mcp.json (auto-starts repomemory in every project)
  • Rules in .cursor/rules/repomemory.mdc (teaches Cursor's AI to use context)
  • 6 commands in .cursor/commands/ (run with / in Cursor chat)

Then in Cursor chat, type:

/repomemory-analyze

Cursor's own AI scans your repo and populates .context/ via the MCP tools. No external API key required — your Cursor subscription handles it.

Available Cursor commands:

Guided wizard

npx repomemory wizard

Walks through provider selection, tool integration, and first analysis. If no API keys are detected, offers a "None — I use Cursor" option that skips external analysis entirely.

Non-interactive (CI-safe)

npx repomemory go --yes --provider anthropic --embedding-provider gemini --max-files 80

No prompts when --yes / --defaults / --no-prompt is used.

MCP Server — Agents With Real Memory

The real power is the MCP server. When configured via repomemory setup claude, it auto-starts with Claude Code and gives agents 7 tools:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Repomemory: common questions

Is Repomemory MCP server safe?
Mostly: it is graded B (82/100). Read the Repomemory safety report
How do I install Repomemory?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Repomemory need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Repomemory maintained?
The last commit was 202 days ago (2026-04-15). The latest release is v1.3.0.
What can I use instead of Repomemory?
Servers from other publishers that do the same job: Misakanet MCP server, M3 Memory MCP server and Reverie MCP server.
How does Repomemory compare with other Web search MCP servers?
safety score 82/100 (higher than 68% of 3,470 Web search servers); tools 7 (the typical Web search server has 5); tools that change things 29% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Repomemory

Same job from other publishers: the closest match first, then the best rated.

  • Misakanet
    Failure-memory layer for coding agents: search evidence-rated failure lessons by error text.
    A
  • M3 Memory
    Local-first, cloud-friendly memory — 100+ tools, 99.2% LongMemEval-S retrieval@8, hybrid search.
    A
  • Reverie
    Graph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search
    B
  • Octobrain
    Persistent memory for AI assistants with semantic search and knowledge graph relationships.
    A
  • Repomix
    Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
    A