This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Persistent, searchable project memory for AI agents, over the Model Context Protocol.
Knownbase is a hosted MCP server that gives AI coding agents (Claude, Cursor, ChatGPT, Claude Code, Windsurf, and any other MCP-compatible client) a place to read and write durable notes, decisions, and handoffs that live outside your git history: the working memory an agent otherwise loses the moment a session ends.
This repository documents the /mcp endpoint: how to connect, what tools it exposes, and how
authentication works. There is no local install: Knownbase is a remote, streamable-HTTP MCP
server, so connecting is just pointing your client at a URL.
https://knownbase.dev/mcpAI agents are stateless between sessions. Every new chat, every new terminal, every restarted IDE window starts from zero. The agent re-reads your code but has no memory of why things are the way they are:
Architecture decisions and the tradeoffs behind them
Debugging trails ("we tried X, it didn't work because Y")
Conventions and gotchas that aren't obvious from the code itself
Task handoffs between sessions, or between you and a teammate's agent
Anything you don't want cluttering git history but still need the agent to know
Without a memory layer, you end up re-explaining the same context every session, or the agent re-discovers (and re-breaks) the same thing twice. Knownbase gives the agent a workspace it can search and write to directly, so that memory persists and compounds instead of resetting.
Related MCP server: memory-vault
Create a free workspace at knownbase.dev (no card required).
Connect your MCP client to https://knownbase.dev/mcp; see
docs/CONNECTING_CLIENTS.md for exact steps per client
(Claude, Claude Code, ChatGPT, Cursor, and generic MCP clients).
Authenticate with either a static API key or OAuth 2.1 (most clients auto-discover OAuth); see docs/AUTHENTICATION.md.
Start a task with get_context to load what's already known, write durable knowledge with
remember, and fall back to search_notes / get_note / upsert_note for direct control.
Full tool reference: docs/TOOLS.md.
Tool | Purpose |
| List project categories and note counts in the workspace |
| One-call project orientation: constraints, decisions, status, open items, and recent changes, ranked and packed to a token budget |
| Search by text, project, tag, status, or last-modified date (keyword; semantic search is coming soon, and |
| Read one note in full, with its links/backlinks |
| Batch-read up to 50 notes in one call |
| Store a durable fact/decision/constraint in one call: derives the title, checks for duplicates or contradictions, reports what it did |
| Close a work session as structured durable state: summary, decisions, discoveries, open items, next actions |
| Resume from another agent, session, or machine via an opaque cursor, without reloading the project |
| Create a note, or partially update an existing one |
| Change part of a body (append, prepend, or literal find-and-replace) without resending it |
| Soft-delete (trash) a note |
| List a note's saved prior versions |
| Read the full body of one historical revision |
| Plan, limits, usage, and this key's own access scope |
| Bulk-rename a project across every note |
| Bulk-rename or remove a tag across every note |
| Export full content of one project inline, for backup/portability |
Notes also carry optional typed, temporal metadata (decision / fact / constraint / …, plus
a current / superseded / disputed lifecycle) that get_context ranks and filters on. See
Typed, temporal memory in the tool reference.
Full parameter-level reference, including the lean-by-default response shapes designed to save agent tokens, is in docs/TOOLS.md.
Every note is scoped to your own workspace; nothing is shared across tenants. Full-text search
runs server-side, so agents get results without loading your entire notes corpus into context.
Semantic (meaning-based) search is coming soon: search_notes already accepts semantic: true
and falls back to keyword search until it is available, and workspace_info reports
plan.semanticSearch so an agent can check first. Notes are versioned (every edit snapshots a
revision) and soft-deleted (trash, not permanently gone), so an agent's write is never a one-way
door.
Homepage: what Knownbase is and who it's for
Pricing: free tier (3 projects, 300 notes, 2 MCP keys), plus Go / Solo / Team / Business plans, each with a 7-day free trial
Blog: guides on MCP, agent memory, and handoffs
llms.txt: machine-readable product/endpoint summary
docs/AUTHENTICATION.md: API keys, OAuth 2.1 flow, project-scoped keys
docs/CONNECTING_CLIENTS.md: per-client setup (Claude, Claude Code, ChatGPT, Cursor, others)
docs/TOOLS.md: full tool reference with input/output shapes
server.json: MCP Registry manifest
This repository documents a hosted service; it does not contain the Knownbase server's source code. Found an issue with these docs, or a mismatch with actual server behavior? Please open an issue or email hello@knownbase.dev.
Documentation in this repository is MIT licensed. Use of the Knownbase service itself is governed by its Terms of Service.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Persistent memory layer for AI tools. Save and recall notes across Claude and other MCP clients.
Agent-native notes, tasks, dev-docs, vaults, sync & handoffs. MCP + OpenAPI dual surface.
A second brain for your AI agent. Shared memory for your team's AI agents, plus public and private knowledge bases — works with ChatGPT, Claude, Cursor and any MCP client.
Hosted MCP memory for coding agents: persistent across sessions, editable markdown, team sharing.
