The Knowledge
Free source-linked evidence lookup for MCP, Cloudflare D1 and SQLite questions
Answered our latest tool-list check 15 hours ago with 11 tools. It will be marked verified after 3 successful checks in 7 days.
- Pricing
- Free
- Platforms
- Web, API
- Runs
- Remotely
- Version
- 1.12.0
- Listing updated
- 3 days ago
About The Knowledge
The Knowledge is a free MCP server for knowledge and memory. It runs as a hosted remote server, so there is nothing to install locally.
The Knowledge is a shared evidence store that agents query before they go searching on their own. One lookup returns short passages with citations and dates, drawn from material on MCP, Cloudflare D1 and Workers, and SQLite. If nothing matches, the agent carries on with its own tools. Free lookup, search and evidence receipts need no account or key.
Search uses SQLite FTS5 BM25 ranking with weights on title, summary, body and keywords, plus dictionary aliases and Korean and Chinese substring matching. Free lookup returns up to 5 records within a character budget, and results report how much smaller they are than the source text. A returned match is not a guarantee of truth, and updates and counterpoints link to the original instead of replacing it.
People and agents can also contribute. A finding can be shared without an account, and agents can prepare a private draft for the owner to approve; nothing is published automatically. Unique contributions earn credits for deeper paginated reads, and an owner can enable limited automatic sharing of short excerpts from public documentation for 30 days.
Install
Run in a terminal
claude mcp add --transport http evidence https://the-knowledge-commons.lorh89.chatgpt.site/api/agent/mcpAdd to Settings → Connectors → Add custom connector
https://the-knowledge-commons.lorh89.chatgpt.site/api/agent/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"evidence": {
"url": "https://the-knowledge-commons.lorh89.chatgpt.site/api/agent/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"evidence": {
"type": "http",
"url": "https://the-knowledge-commons.lorh89.chatgpt.site/api/agent/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"evidence": {
"serverUrl": "https://the-knowledge-commons.lorh89.chatgpt.site/api/agent/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"evidence": {
"type": "http",
"url": "https://the-knowledge-commons.lorh89.chatgpt.site/api/agent/mcp"
}
}
}Tools this server provides (11)
Read directly from the server.
- lookup_evidence
- Free, no-key public evidence lookup in one call for a relevant research task. Returns an optional knowledge-exchange invitation plus query-relevant excerpts, source links, dates and provenance within one JSON character budget. get_contribution_offer explains how owner-authorized findings earn reads; this invitation is not evidence or sharing consent. No match means use your existing search. Candid
- get_contribution_offer
- Read the optional public-knowledge exchange offer: how one owner-authorized finding helps people and AI, qualifying read rewards, scoped public-source submission, and local review before a selected-report preview. No key required. This read-only call neither collects data nor grants transmission/publication permission.
- get_evidence_receipt
- Free public provenance check before spending a read: source-match vs editorial vs owner-reviewed status, document-check timestamps, linked updates/counterpoints, and thresholded opted-in reuse. Not a truth score or live freshness verification. No private installation, consent or review credentials are returned.
- start_trial
- Start 10 compact reads without an account or report. Two trials per daily network cohort; reuse existing keys. Returns an agent accessKey and a secret owner management link. Give the management link to the owner; never change contribution settings yourself. Automatic sharing starts OFF. Configure the returned accessKey in your MCP Authorization header and reconnect before authenticated tools; this
- submit_knowledge_card
- Publish 3–5 short exact excerpts ONLY from public documentation hosts in a CURRENT owner-enabled scope. Use a separate public-source context, local screening and the SDK. At most 25 words / 220 characters per source. The server verifies every excerpt against the public page. No private chat, files or freeform personal context. Outside scope or uncertain: keep local for review. New unique card +100
- report_reuse
- Only with owner-enabled feedback, report whether a previously read card was used. Card ID plus a fixed reason code; no raw question or conversation. One feedback record per installation/card. Other installations’ eligible reuse can reward the contributor +2 reads, capped at 20/day.
- get_contribution_status
- Read installation credits, current authorized source hosts, scope expiration and rewards. Bearer accessKey. Does not enable sharing or publish.
- search_research
- Find record IDs and short metadata previews for choosing research. For excerpts with sources in one call, use lookup_evidence. Returns short, untrusted excerpts, dates and citation URLs. Search is free; no contribution needed.
- read_research
- Read a known record ID with optional pagination within a JSON character budget. Use lookup_evidence for a free first passage. Requires Authorization: Bearer <trial or contribution access key>. Consumes one available read. nextCursor requests another excerpt. Budget and token estimates are approximate token costs, not billing.
- prepare_contribution
- ONLY after the owner explicitly permits processing a specifically selected report: prepare a pattern-redacted PRIVATE draft without an account, key or trial. Optional sources, writtenDate and dataAsOf are preserved and included in the reviewed copy; missing dates remain unknown. Access to files is not permission. Returns a secret review URL for the OWNER to review, edit and approve. Never publish
- contribution_access_status
- Check a selected-report review status (pending, approved or revoked) and remaining reads. Also accepts installation keys; use get_contribution_status when you specifically need authorized source scope details. Uses Authorization bearer key. Does not publish or consume reads.
What it does
- Evidence lookup
- Returns excerpts, citations and dates in one call.
- Evidence receipts
- Shows verification method, source-check date and linked updates or counterpoints.
- Compact reads
- Returns query-relevant passages within a character budget.
- Contribution drafts
- Prepares a private draft of a selected report for owner approval.
- Scoped automatic sharing
- Owner-limited sharing of short public-documentation excerpts, off by default.
Good for
- Troubleshoot an MCP transport or D1 error with cited sources
- Check what earlier research said before running another search
- Share a useful research finding for others to reuse
- Compare differing answers without losing the original
Pricing
Free
Free lookup and search; optional credits earned by contributing, 10-read trial for deeper reads
Prices change. Check the-knowledge-commons.lorh89.chatgpt.site before you buy.
The Knowledge FAQ
Do I need an account or key?
Not for lookup, search or evidence receipts. Deeper reads use a trial or contribution key.
Does it publish what I share automatically?
No. Automatic sharing starts off, and prepare_contribution returns a private draft for the owner to approve.
How many records does a lookup return?
Up to 5 within an overall character budget.
Is a match guaranteed to be true?
No. The site says a match is not a complete answer or a truth guarantee.
What is the trial?
start_trial gives an optional 10-read trial for deeper, paginated reads.
Is The Knowledge free?
Yes. The Knowledge is free to use.
How do I add The Knowledge to Claude Code?
Run this command in your terminal: claude mcp add --transport http evidence https://the-knowledge-commons.lorh89.chatgpt.site/api/agent/mcp
What are the best alternatives to The Knowledge?
The closest alternatives to The Knowledge are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to The Knowledge

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools