M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
M

MisakaNet MCP Server

Community
Git-backed failure memory for AI coding agents.
How to install ↓ Compare GitHub source repository ↗
Category
Dev Tools #227 of 438
Stars
★ 529 Very popular
Transport
stdio (local process)
Runtime
Python 3.10+ · Hosted (no local runtime)
Credentials
API key / credential required
License
Apache-2.0
Last commit
52FMRS · D

The source positions MisakaNet as a failure-recovery knowledge layer for AI coding agents, not as general memory, an agent runtime, or a vector database. It clearly supports local stdio execution and provides a remote Bearer-token configuration example, but it does not list specific MCP tool names, so the tools list is empty.

Strongest · Documentation 13/20 Weakest · Reliability 6/20

Reliability
6/20
Security and permissions
9/20
Maintenance
13/20
Documentation
13/20
Setup experience
11/20
Why each score
Reliability 6/20
The manifest declares a Python stdio entry point at scripts/mcp_server.py, but no tool list, parameter schema, initialization-handshake implementation, or committed tests are provided. The README claims v2.17.0 while the manifest and package metadata state 2.15.0, creating a material version contradiction. Startup is plausible, but MCP behavior, failure handling, and key paths cannot be statically verified, so substantial points are deducted.
Security and permissions 9/20
The evidence shows a Bearer-token remote MCP and a local mode that supposedly needs no server. The README warns that community lessons may contain dangerous commands and recommends sandboxing, and claims path-traversal, XSS, and email-redaction hardening. However, none of those implementations can be verified from the supplied source, and permission scope, data flows, external network behavior, and confirmation requirements are not documented. No explicit credential theft or destructive-by-default behavior is shown, so the red-line score of 0-4 is not triggered.
Maintenance 13/20
The repository is not archived and the supplied material identifies an Apache-2.0 license, CI badge, multiple releases, security-related documentation, and an ongoing contribution roadmap. These signals are primarily README claims; there is no reviewable commit history, release evidence, dependency-update record, or maintainer response evidence in the source provided. The inconsistent versioning also prevents a near-full score.
Documentation 13/20
The README explains the purpose and non-goals, lists CLI and MCP commands, provides remote configuration, contribution paths, limitations, security warnings, and links to additional documentation. It does not provide the actual MCP tool definitions, complete parameter and return schemas, authentication lifecycle, permission boundaries, cost information, or verifiable troubleshooting/test evidence. The version and package-name inconsistencies further reduce confidence.
Setup experience 11/20
Python 3.10+, a stdio launch command, a remote MCP URL, and a client JSON example are provided, making the basic path understandable. However, the manifest PyPI identifier differs from the README-linked misakanet-core package, remote pairing/token setup depends on an external site, and mainstream-client compatibility, installation verification, and execution tests are not supplied. Setup therefore appears possible but remains moderately manual and insufficiently verified.

Static review · not runListed 2026-08-14

Read the FMRS scoring method →

Fit and risk

What it can accessUses the network

Best for

  • AI coding agents that need failure-recovery knowledge during task execution
  • Developers who want public debugging knowledge managed with Git and Markdown
  • Users who prefer zero-dependency, database-free deployment

Not for

  • A general-purpose memory system
  • An AI-agent runtime or framework
  • A vector database or RAG system
  • A skill marketplace

Required permissions

  • Local stdio setup requires running Python 3 and accessing the MisakaNet source and lesson files
  • Remote MCP setup requires using the supplied Bearer token to access the remote endpoint
  • Contributing or submitting an intake report requires intentional submission of content

Risks and side effects

  • Lessons are community-contributed; review and sandbox commands before executing them
  • A retrieved fix may not apply to the current environment
  • Remote use involves sending searches to the service and handling an access token

Setup

Before you start

Runtime：Python 3.10+ · Hosted (no local runtime)

Remote setup: visit https://misakanet.org/connect to generate configuration, then add it to the client. The configuration uses https://misakanet.org/mcp with a Bearer token. The source documents local MCP startup with python3 scripts/mcp_server.py.

.cursor/mcp.json 
{"mcpServers":{"misakanet":{"url":"https://misakanet.org/mcp","headers":{"Authorization":"Bearer YOUR_TOKEN"}}}}

Shown for Cursor. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

.vscode/mcp.json
{
  "servers": {
    "misakanet": {
      "url": "https://misakanet.org/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_TOKEN"
      }
    }
  }
}

Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).

Terminal
claude mcp add --transport http misakanet https://misakanet.org/mcp --header 'Authorization: Bearer YOUR_TOKEN'

Run it in a terminal; replace any <…> placeholders with your own values first.

Generate and validate client config

Check that it works

Add https://misakanet.org/mcp to your MCP config with a Bearer token generated at https://misakanet.org/connect, then ask "Search MisakaNet for database locked" — a returned fix path proves the connection works.

Troubleshooting

  1. Confirm Python 3 is available and run python3 scripts/mcp_server.py from the correct MisakaNet directory
  2. For remote setup, verify the endpoint is https://misakanet.org/mcp and the Bearer token is valid
  3. Search using the specific error text or relevant keywords, then check each lesson's verification steps
  4. Confirm the client supports MCP and has loaded the configuration correctly

Things to try

Once connected, you can ask your AI assistant things like:

  • Search MisakaNet for database locked
  • Search MisakaNet for pip install timeout
  • Search MisakaNet for GitHub 401 token expired
  • Search MisakaNet for DCO sign-off failure

Use cases

Search recovery lessons for DCO, pip timeouts, GitHub 401 errors, MCP setup, and encoding issues
Find documented fix paths when CI failures or recurring errors occur
Provide AI agents with shared, auditable debugging experience

Supported clients

CursorPartial support
Claude CodePartial support
CodexPartial support

Listed from the project's documentation, not tested by this site.

Overview

MisakaNet is a zero-dependency, Git-backed failure-recovery knowledge layer that searches documented debugging experiences and returns fix paths for AI coding agents. It uses the Python standard library and BM25 keyword search, and is available through MCP, CLI, or intake.

Similar servers

Context7 80 · B

Upstash's official server providing up-to-date third-party library docs for AI coding assistants

★ 63.3k · Tools 2 Compare with this →
Compare with other MCP servers

Source revision 45f279fd780d Data synced 2026-10-19 Read the FMRS scoring method