Knownbase MCP
About
Persistent, searchable project memory for AI agents, over the Model Context Protocol.
Details
- Author
- zeeshandev6
- Categories
- AI
Jump to
Setup
Install Knownbase MCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/zeeshandev6/knownbase-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
Persistent, searchable project memory for AI agents, over the Model Context Protocol.
This repository documents the/mcpendpoint: 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.
AI 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 ofwhythings 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.
- Create a free workspace atknownbase.dev(no card required).
- Connect your MCP client tohttps://knownbase.dev/mcp; seedocs/CONNECTING_CLIENTS.mdfor 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); seedocs/AUTHENTICATION.md.
- Start a task withget_contextto load what's already known, write durable knowledge withremember, and fall back tosearch_notes/get_note/upsert_notefor direct control. Full tool reference:docs/TOOLS.md.
Notes also carry optional typed, temporal metadata (decision/fact/constraint/ …, plus acurrent/superseded/disputedlifecycle) thatget_contextranks and filters on. SeeTyped, temporal memoryin the tool reference.
Full parameter-level reference, including the lean-by-default response shapes designed to save agent tokens, is indocs/TOOLS.md.
Every note is scoped to your own workspace; nothing is shared across tenants. Full-text search (and, on supported plans, semantic/meaning-based search) runs server-side, so agents get results without loading your entire notes corpus into context. 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
- Features
- 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
- Contact·hello@knownbase.dev
- 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 Registrymanifest
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? Pleaseopen an issueor emailhello@knownbase.dev.
Documentation in this repository isMIT licensed. Use of the Knownbase service itself is governed by itsTerms of Service.
Local-first agent memory: a plain-Markdown Obsidian vault is the source of truth, with a rebuildable DuckDB index for hybrid BM25 + vector + graph recall.
Persistent memory and semantic search for AI coding assistants across sessions
Give your agent a memory: shared, cited, tenant-isolated knowledge-graph memory for any MCP host. Grounded answers from a local-first June endpoint — abstains rather than guesses.
Decentralized persistent memory for AI agents — encrypted vault storage built on Walrus and Sui.
Persistent memory for AI assistants and coding agents across ChatGPT, Claude, Cursor, and other MCP-compatible tools.
Your portable AI memory vault — memories, skills & configs, shared across every AI tool.
Local Work Model for AI agents that learns from real outcomes.
Adaptive MCP memory system for AI applications. Learns which retrieval strategies work for your data, scores results using cognitive science models, builds a knowledge graph automatically, and validates every parameter change against real query history before adopting it. Patent pending.
Auditable, self-improving knowledge & memory for AI agents over MCP — citation-enforced answers and a replayable why-trace, self-hosted on Postgres.
Turns your task manager into agent memory: hybrid (RRF) retrieval over TickTick or an Obsidian vault via an adapter contract. MCP server + CLI, no vector DB to maintain.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
