Get This Tool
Mwe-MCP
Pricing
- Model
- Free
Summary
Every agent you spin up starts with amnesia — and when three agents share a codebase but can't share context, you spend more time reconstructing state than building features. mwe-mcp solves that by giving all your agents one persistent, structured memory store they can read and write over MCP.
The store lives on your own server as human-readable Markdown files, which means you can open a file, spot a hallucinated fact, and correct it without touching any agent code. Per-fragment access controls let you scope which agents or users can read or write each memory entry — so a household assistant and a work agent can coexist without leaking context across boundaries. The docs describe an overnight self-organizing pass that restructures the wiki without agent intervention. Where this breaks: teams expecting a managed cloud endpoint will find none — the vendor states AGPL self-hosted only. Standing up and maintaining the server is your problem.
Bottom line: Pick this when you need auditable, shared agent memory you can host and inspect yourself; plan a different architecture when your team cannot own server operations or needs a hosted API with an SLA.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- Human-readable Markdown storage, so you can audit, correct, or delete any memory fragment with a text editor — without writing agent code or issuing API calls to fix a hallucinated fact that would otherwise silently propagate.
- Per-fragment ACL at the memory level, which means a single server instance can serve agents with different trust levels or different users without leaking cross-context data — avoiding the need to run separate memory servers per tenant.
- Agent-agnostic MCP interface, so any framework that speaks Model Context Protocol can attach without a custom adapter — swapping or adding agent frameworks does not require migrating the memory backend.
- Self-hosted under AGPL with no external dependency, which means your memory store does not go down when a third-party API has an outage and your data does not leave your infrastructure.
- API available, so agents that prefer direct programmatic access over the MCP layer have a path without being forced through a protocol they may not support natively.
Cons
Sign in to edit- No hosted option exists — the vendor states AGPL self-hosted only. Teams without server infrastructure or ops capacity hit this wall before writing a single agent integration, and they switch to a managed memory service that trades auditability for a working endpoint.
- The overnight self-organizing pass runs on a fixed schedule rather than on demand. Agents that write high volumes of facts during the day work against a wiki that may be structurally stale until the next reorganization cycle — teams with real-time coherence requirements add a manual trigger layer or accept the lag.
- AGPL licensing means any commercial product that ships with mwe-mcp linked in must open-source the combined work. Teams building proprietary software review the license, conclude they cannot comply, and move to a permissively licensed alternative regardless of the technical fit.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- Linux, macOS, Windows (self-hosted)
- API Available
- Yes
- Self-Hosted
- Yes
- Last Updated
- 2026-07-25T08:15:59.267Z
Best For
Who it's for
- Developers wanting transparent, file-based agent memory
- Any MCP-compatible agent framework
What it does well
- Shared long-term memory across multiple AI agents
- Human-readable fact store that can be audited and corrected directly
- Multi-user memory with fine-grained per-fragment permissions
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is Mwe-MCP free?
- Yes — Mwe-MCP is fully free to use. There is no paid tier.
- Is Mwe-MCP open source?
- Yes. Mwe-MCP is open source.
- Does Mwe-MCP have an API?
- Yes. Mwe-MCP exposes a developer API. See the official documentation at https://github.com/fr4nz82/mwe-mcp for details.
- Can I self-host Mwe-MCP?
- Yes. Mwe-MCP supports self-hosting on your own infrastructure.
- What platforms does Mwe-MCP support?
- Mwe-MCP is available on: Linux, macOS, Windows (self-hosted).
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Most agent memory lives inside a single session, inside a single model, invisible to anything else running in your stack. mwe-mcp is a self-hosted Model Context Protocol server that exposes a shared Markdown wiki as persistent memory — agents read from it and write to it through standard MCP calls, and the files sit on disk where any human can open them. The core workflow is: agent makes an MCP call to read or store a fact, the server writes or retrieves a structured Markdown fragment, and every other MCP-compatible agent on the same server sees the same state.
The differentiating feature is the human-readable, file-based store combined with per-fragment access control lists. Unlike vector stores or opaque database backends, every memory entry is a Markdown file you can audit, edit, or delete directly. The ACL system lets you assign read and write permissions at the individual fragment level, so multi-user and multi-agent deployments can share infrastructure without sharing every secret — a design that matters when you’re mixing personal and professional agents on the same host.
The tool fits teams or individual developers who want transparent, governable agent memory and are willing to run their own server. It does not fit teams that need a hosted endpoint, an SLA, or a managed upgrade path. The AGPL license also means any product you ship that links against the server inherits that license — legal review is required before embedding it in a commercial product. The overnight self-organizing pass that restructures the wiki is described in the docs, but the behavior under large or rapidly growing wikis is not detailed in the available source material.