Engram
Gives Claude access to your repository's git history and test suite to prevent "fix one thing, break another" scenarios. Exposes three core tools: get_impact_analysis surfaces files that frequently changed together with your target file and extracts test intent strings from specs across Jest, Pytest, JUnit, and others; save_project_note and read_project_notes create a persistent knowledge base for architectural constraints that aren't in the code. The Rust core indexes commit history and builds a SQLite database of temporal coupling, so when you're about to modify a file, Claude can see the hidden dependencies and behavioral requirements before writing code. Designed for local execution with zero telemetry.
- GitHub stars
- 6
- tools
- 3
- transport
- STDIO
- last updated
- Feb 10, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
get_impact_analysisBlast radius calculation for a target file: returns the impacted files, their test intents and any stored notes.
Blast radius calculation for a target file: returns the impacted files, their test intents and any stored notes.
No parameter schema in public metadata yet.
save_project_noteStore persistent notes that automatically appear in future impact analyses.
Store persistent notes that automatically appear in future impact analyses.
No parameter schema in public metadata yet.
read_project_notesSearch notes by content or file path, or list all project knowledge.
Search notes by content or file path, or list all project knowledge.
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
Engram
The "Missing Context" Engine for AI Agents.
Engram gives your AI agent the context it can’t see in the code alone.
While LLMs are excellent at analyzing the specific files you give them, they lack the broader context of your repository's history and guardrails. Engram bridges this gap by surfacing hidden dependencies (via git history) and required behaviours (via test intents) that the AI would otherwise not have access to, miss or ignore.
Why Engram?
- Temporal History: Answers "What usually changes when this file changes?" to prevent the "fix one thing, break another" cycle.
- Test Intent: Extracts test intent strings (e.g., "should handle negative balance") so the AI understands what behaviour to preserve.
- Organizational Memory: A persistent store for you or the LLM to record undocumented architectural constraints, ensuring lessons learned aren't lost when you start a new conversation.
Built for Privacy. Public for Integrity.
Details
- Repository
- github.com/spectra-g/engram
- Category
- AI & LLM Tools
- Package
@spectra-g/engram-adapter- Transport
- STDIO
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Writbasewritbase/writbaseMCP-native task management for AI agent fleets with scoped permissions and provenance.6stars
Qemu Mcp0xmortuex/qemu-mcpBoot and drive QEMU VMs from an AI agent: keys, screenshots, serial. No guest agent.5stars
HasData Binghasdata/bing-mcpBing search results with the ad block and Copilot answer, geo and market targeting, as JSON.5stars
Silicon Friendlyunlikefraction/silicon-friendlyDirectory rating websites on AI-agent-friendliness. Search, lookup, and submit.5stars
TickerDBtickerdb/tickerdb-mcpPre-computed market data that improves agent reasoning, reduces token usage, and replaces pipelines.5stars
Skill Audit Mcpeltociear/skill-audit-mcpMCP server: static security scanner for MCP servers, agent skills & plugins. 17 attack patterns.5stars