Grounded Knowledge Engine MCP server
Commit Nov 12, 2026Provides AI agents with durable project memory by grounding answers in local Markdown files and capturing new learnings back into the knowledge base.
Also known as dimosgit/grounded-knowledge-engine
- Stars
- 5
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 12, 2026
- License
- MIT
What is Grounded Knowledge Engine MCP?
Grounded Knowledge Engine provides AI agents with durable project memory by grounding answers in local Markdown files and capturing new learnings back into the knowledge base.
Summary generated from the project's README
About Grounded Knowledge Engine MCP server
Providing AI coding agents with durable project memory through local Markdown files is the primary function of this tool. It allows developers using Claude Code, Codex, Gemini CLI, or Copilot to maintain context across different sessions by grounding answers in local evidence. The system uses a local-first approach where your Markdown files remain the source of truth while retrieval indexes are generated as disposable assets on your machine.
Users interact with the server through a core profile containing tools like kb.search, kb.get_record, kb.answer_and_capture, and kb.resume_project. The engine can ingest various document formats including PDF, DOCX, XLSX, PPTX, and HTML to expand the knowledge base. While named workspaces start with writes disabled, the default setup allows agents to automatically append new findings to existing records. This setup requires Node 22.5 or newer to function correctly.
What you can do with it
- 1Resuming interrupted development tasksAsk your AI agent to pick up exactly where a previous session left off using a cited briefing.
- 2Automating knowledge retentionHave the agent automatically save new technical discoveries directly into your project documentation.
- 3Searching local project documentationRetrieve specific information from your codebase with precise file and line number citations.
- 4Ingesting external project filesAdd context to your workspace by importing various document types like spreadsheets or presentations.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachabledimosgit/grounded-knowledge-engine is public and reachablegithub.com/dimosgit/grounded-knowledge-engine ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-12github.com/dimosgit/grounded-knowledge-engine ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubGrounded Knowledge Engine
Local-first, provider-neutral project memory for AI coding agents.
Grounded Knowledge Engine (GKE) gives Claude Code, Codex, Gemini CLI, and other MCP clients durable context across sessions. It retrieves evidence from local files, answers with file-and-line citations, retains useful learning back into Markdown, and resumes structured project state without turning a database or hosted service into the source of truth.
Your Markdown remains canonical. Retrieval indexes are derived and disposable, and every workspace stays on your machine.
https://github.com/user-attachments/assets/d00c977b-9538-4835-94d5-26350136eb34
What GKE does
- Grounded answers with file-and-line citations and strict abstention.
- Durable capture back into Markdown; risky changes enter a review queue.
- Project resume as a cited briefing: focus, decisions, blockers, next steps.
- Document ingestion for PDF, DOCX, XLSX, PPTX, HTML, and more.
- One local MCP server for Claude Code, Codex, Gemini CLI, and Copilot.
It is not a hosted chat memory, team wiki, or document-management platform.
Quick start
GKE requires Node 22.5 or newer; Node 24 is recommended.
Install the current release:
npm install --global https://github.com/dimosgit/grounded-knowledge-engine/releases/download/v0.2.2/grounded-knowledge-engine-0.2.2.tgz
Create the verified demo workspace and configure supported clients:
gke demo
cd gke-demo
gke setup
Restart Claude Code or Codex from gke-demo, then ask:
Use GKE to resume the router-rollout project.
Continue with the five-minute golden path to retrieve cited evidence, retain one learning, and retrieve it again from a fresh session.
The core loop
Index or ingest local evidence, answer with citations, capture what was learned back into Markdown, and resume the project in a later session.
MCP surface
The default core profile exposes four tools: kb.search, kb.get_record,
kb.answer_and_capture, and kb.resume_project. When writes are enabled,
retention is automatic and update-first: when the agent establishes a finding
the knowledge base lacked, it is appended to the record that owns it, without
asking first. The demo and default workspaces enable writes; named workspaces
start with writes disabled. The full profile adds
advanced retrieval, decisions, and explicit write tools. See the
MCP server reference.
Your own workspace and documents
gke setup --workspace client-alpha --workspace-root "/path/to/client-alpha"
npm run ingest -- ./inbox --dry-run
Each named workspace runs as its own process, with writes disabled by default. See workspace configuration and the ingestion guide.
Operator Cockpit
An optional local view for project attention, capture and decision review, and a context graph. Try the public demo or read the Cockpit guide.
Learn more
Golden path · Boundaries · Data model · Copilot · Agent workflows · Contributing
License
MIT. The demo knowledge base includes paraphrased notes from the MIT-licensed MCP documentation; see demo sources.
Grounded Knowledge Engine MCP questions
What file formats can GKE ingest?
The engine supports document ingestion for PDF, DOCX, XLSX, PPTX, HTML, and more.
Does GKE store my data in a cloud database?
No, it is a local-first engine where every workspace stays on your machine and your Markdown remains the canonical source of truth.
How does the engine handle new information learned by the AI?
When writes are enabled, the agent automatically appends new findings to the relevant Markdown record without asking first.