Skip to main content
MCP server CX Codex

engram · girishbuilds — Claude Code MCP server: repo memory for agents

Tells your agent which files tend to change together and what the tests expect. Useful before touching unfamiliar code.

Install into Claude Code · Platform CLI All methods and platforms ↓
claude mcp add engram -- npx -y @spectra-g/engram-adapter
Open on GitHub

What engram does

Engram is an MCP server that hands the agent context the files themselves don't carry. It mines git history for files that keep getting committed alongside your target, so a change to A.ts comes with a warning about B.ts. The second layer is tests: it pulls out intent strings such as it("should validate JWT expiration") and passes them along as behavioural guardrails.

Notes are the third layer. The agent calls save_project_note to record what the code doesn't say — field order in an export format, a restart needed after a config change. Those notes then surface on their own in later impact analyses. Three tools in total: get_impact_analysis, save_project_note, read_project_notes.

Everything runs on your machine, with no telemetry. The adapter is a TypeScript server on Node.js, started through npx and speaking stdio. Test framework coverage is uneven: JS/TS (Vitest, Jest, Mocha, Playwright, Cypress), JVM (JUnit 4, JUnit 5, Kotest, ScalaTest), Rust, Python (Pytest, Unittest) and Go. Point it at anything else and no intent strings get collected, which costs you half the value.

What it helps with

  • spot hidden coupling between files before editing
  • keep a positional parser in another file from breaking
  • read test intent without opening the whole suite
  • carry project knowledge across agent sessions
  • size up the blast radius of one file change

Example prompts for the agent

  • Run an impact analysis on src/Auth.ts with engram
  • Save a project note: the export line format is parsed positionally by bin/legacy-mainframe-sync.js
  • Search project notes for Redis

How to install engram

Platform CLI

claude mcp add engram -- npx -y @spectra-g/engram-adapter

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about engram

How do I install engram in Claude Code?

Run claude mcp add engram -- npx -y @spectra-g/engram-adapter.

What does engram do?

It builds a graph from git history and tests, reports coupled files, and stores project notes. The agent queries it before writing code.

Which test frameworks does it support?

Vitest, Jest, Mocha, Playwright and Cypress for JS/TS; JUnit 4 and 5, Kotest and ScalaTest for the JVM; native Rust; Pytest and Unittest for Python; native Go.

Similar MCP servers

All MCP servers for Agent setup: memory, context, orchestration →

engram by other authors comes first.

engram NickCirv Builds a local graph of your codebase and hands the agent the relevant files and links instead of everything at once. Fits projects that no longer fit in context. CX Codex +1 ★ 143repo stars engram tstockham96 Stores project knowledge locally and helps an agent retrieve it by meaning. Useful when context needs to carry across sessions and projects. CX Codex +1 ★ 47repo stars engram kael-bit Hierarchical memory engine with three-stage retention and decay for AI agents. Keeps essential project context alive across session restarts. CX Codex +1 ★ 28repo stars Engram get-engram Keeps every agent conversation word for word and finds it again by meaning. One shared memory across Claude, Codex, Cursor, Copilot and Zed. CX Codex +1 ★ 19repo stars Engram rwnalds Engram gives agents a shared Markdown vault backed by Git and filters out notes marked as outdated. It suits projects where multiple agents need to read and update the same knowledge base. CX Codex +1 ★ 17repo stars REA morluto Analyzes binaries, Electron bundles, and JavaScript runtimes directly from your agent. It inspects compiled apps without source code to recreate specific features. CX Codex +1 ★ 386,989repo stars GitHub official github Wires your AI agent into GitHub: read code, open issues and pull requests, watch Actions runs. Saves a trip to the browser. CX Codex +1 ★ 33,918repo stars Netdata netdata Hands your AI agent live monitoring data: metrics, logs, alerts and anomaly detection. Useful when you need to know what a server is doing without opening the dashboard. CX Codex +1 ★ 81,115repo stars browser-use browser-use Give an agent browser tasks such as finding information, extracting page data, and filling forms. Connect it when those actions need to happen on the web. CX Codex +1 ★ 119,160repo stars Codebase Memory DeusData A local MCP server that maps your repo's code, docs and infrastructure into a graph. Gives the agent structural context without re-reading files. CX Codex +1 ★ 47,392repo stars mcp-server HeyPuter Connects your AI agent to Puter for files, websites and workers. Useful when the project already lives in Puter's cloud. CX Codex +1 ★ 43,872repo stars

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor