Skip to main content
Glama
MidOS Research Protocol

MidOS Research Protocol

midos-mcp

MidOS MCP Community Library — Knowledge, Skills, and Research as MCP tools.

Install once, connect to any AI client.

Install

pip install midos-mcp

Requirement: MidOS knowledge base must be available locally. Set the MIDOS_ROOT environment variable to point to your MidOS installation directory (the one containing knowledge/ and modules/).

export MIDOS_ROOT=/path/to/midos

Related MCP server: Code-MCP

Quick Start

# Start server (stdio — default for Claude Code, Cursor, etc.)
midos-mcp serve

# Start with HTTP transport
midos-mcp serve --http

# Generate config for your AI client
midos-mcp config --generate claude
midos-mcp config --generate cursor

# Check health
midos-mcp health

Commands

midos-mcp serve

Start the MCP server with your preferred transport.

midos-mcp serve              # stdio (default)
midos-mcp serve --http       # Streamable HTTP on 127.0.0.1:8419
midos-mcp serve --sse        # Legacy SSE transport
midos-mcp serve --http --host 0.0.0.0 --port 9000

Flag

Transport

Use Case

--stdio

stdio

Claude Code, Cursor, Cline (default)

--http

Streamable HTTP

Web clients, remote access

--sse

Server-Sent Events

Legacy clients

midos-mcp config

Generate ready-to-paste JSON config for any supported MCP client.

midos-mcp config --generate claude    # Claude Desktop / Claude Code
midos-mcp config --generate cursor    # Cursor IDE
midos-mcp config --generate cline     # Cline (VS Code)
midos-mcp config --generate windsurf  # Windsurf IDE
midos-mcp config --generate continue  # Continue.dev
midos-mcp config --generate zed       # Zed Editor
midos-mcp config --generate opencode  # OpenCode
midos-mcp config --generate http      # Generic HTTP client

# Write to file
midos-mcp config --generate claude -o mcp-config.json

midos-mcp health

Check server health: knowledge base stats, vector store status, dependencies.

midos-mcp health          # Human-readable output
midos-mcp health --json   # JSON output for scripts

midos-mcp keys

Manage API keys for tiered access control.

midos-mcp keys generate --name "my-app" --tier dev
midos-mcp keys list
midos-mcp keys revoke midos_sk_abc

Tiers: dev (free), pro ($10/mo), admin.

Configuration

Environment Variables

Variable

Default

Description

MIDOS_ROOT

auto-detect

Path to MidOS installation (required)

MIDOS_HOST

127.0.0.1

HTTP server bind host

MIDOS_PORT

8419

HTTP server bind port

MIDOS_TRANSPORT

stdio

Default transport

Root Detection

The server locates the MidOS knowledge base:

  1. MIDOS_ROOT environment variable (recommended)

  2. Auto-detect: walks up from package location looking for CLAUDE.md + knowledge/

  3. Fallback: current working directory

If you installed via pip, auto-detect won't find the knowledge base. Either:

# Option A: Clone the repo and point to it
git clone https://github.com/MidOSresearch/midos.git
export MIDOS_ROOT=./midos

# Option B: Point to an existing MidOS directory
export MIDOS_ROOT=/path/to/your/midos

Verify with midos-mcp health — it shows the detected root and knowledge counts.

Supported Clients

Client

Config File

Transport

Claude Desktop

claude_desktop_config.json

stdio

Claude Code

.mcp.json

stdio

Cursor

.cursor/mcp.json

stdio

Cline

cline_mcp_settings.json

stdio

Windsurf

~/.codeium/windsurf/mcp_config.json

stdio

Continue.dev

~/.continue/config.json

stdio

Zed

~/.config/zed/settings.json

stdio

OpenCode

opencode.json

SSE

Optional Dependencies

# Vector store support (LanceDB + embeddings)
pip install midos-mcp[vector]

# Development tools
pip install midos-mcp[dev]

What's Inside

MidOS exposes 68 MCP tools across 2 tiers:

Tier

Tools

Access

Dev

34 tools

Free — no API key needed, full content, 500 queries/month

Pro

68 tools

$10/mo — security ops, AOTC, orchestration, maker write ops

Capabilities

  • Knowledge — Search 46K+ curated chunks across all domains (full content, no truncation)

  • Skills — 119 reusable patterns across 16+ technology stacks

  • EUREKA — 383 validated improvements with measured ROI

  • Truth — 50 verified patches and corrections

  • SOTA — 140 state-of-the-art convergence ceilings

  • Vector Search — Semantic search via LanceDB + Gemini embeddings (3072-d)

Rate Limits

Tier

Queries/month

Content

Dev

500

Full content (no truncation)

Pro

100,000

Full content + AOTC + ops packs

Invalid or expired API keys silently fall back to Dev tier.

Requirements

  • Python 3.10+

  • FastMCP 2.x

  • MidOS knowledge base (local)

License

MIT

Available Tools

18 tools
agent_bootstrapA

[DEPRECATED -- use agent_handshake instead] Generic agent onboarding. Returns default config for unknown agents.

Inputs: no named parameters. Returns: Generic wrapper for non-object return types.

agent_handshakeA

Personalized agent onboarding. Declare your environment and get optimal config.

Call this FIRST when connecting to MidOS. Pass as much info as you know. Unknown fields can be left empty -- you'll get sensible defaults.

Args: model: Your model ID (e.g. 'claude-opus-4-6', 'gemini-2.5-pro', 'opus') context_window: Your context window in tokens (e.g. 200000). 0 = auto-detect from model. client: Your CLI/IDE (e.g. 'claude-code', 'cursor', 'windsurf', 'cline') languages: Comma-separated languages (e.g. 'python,typescript') frameworks: Comma-separated frameworks (e.g. 'fastapi,react') platform: Your OS (e.g. 'windows', 'linux', 'macos') project_goal: What you're working on (e.g. 'manga engine with SVG rendering')

Inputs: model, client, platform, languages, +3 more. Returns: Generic wrapper for non-object return types.

chunk_codeA

Parse code file into semantic chunks (functions, classes, methods) for better RAG retrieval.

Args: file_path: Path to code file to chunk

Inputs: file_path (required). Returns: Generic wrapper for non-object return types.

episodic_storeA

Store a new episodic memory/reflection for future learning.

Args: task_type: Type of task: CODE, RESEARCH, DEBUG, REVIEW input_preview: Brief description of the input/context success: Whether the task was successful

Inputs: task_type (required), input_preview (required), success. Returns: Generic wrapper for non-object return types.

get_eurekaB

Get a specific EUREKA breakthrough document.

Args: name: EUREKA name (e.g., 'EUREKA_CACHE_SEMANTICA' or 'ATOM_001')

Inputs: name (required). Returns: Generic wrapper for non-object return types.

get_protocolC

Get a specific protocol document.

Args: name: Protocol name (e.g., 'PROTOCOL_NEURAL_LINK')

Inputs: name (required). Returns: Generic wrapper for non-object return types.

get_skillB

Get a specific skill/capability document by name.

Args: name: Skill name (e.g., 'RAG_SYSTEMS_2026_SOTA')

Inputs: name (required). Returns: Generic wrapper for non-object return types.

get_truthC

Get a specific truth patch document.

Args: name: Truth patch name (e.g., 'AGENT_MITIGATIONS_CONTEXT_OVERFLOW')

Inputs: name (required). Returns: Generic wrapper for non-object return types.

hive_statusB

Get current status of the Midos hive system.

Inputs: no named parameters. Returns: Generic wrapper for non-object return types.

list_skillsA

List all available skills/capabilities.

Args: filter: Optional filter for skill names stack: Optional stack filter, comma-separated (e.g. 'python,react'). Skills with matching compatibility.json are prioritized.

Inputs: stack, filter. Returns: Generic wrapper for non-object return types.

memory_statsA

Get statistics about the Midos memory system (LanceDB chunks, cache status).

Inputs: no named parameters. Returns: Generic wrapper for non-object return types.

pool_signalC

Signal an action to the multi-instance coordination pool.

Args: action: Action type: 'completed', 'blocked', 'claimed', 'signaling' topic: Topic/task name summary: Brief description of the action affects: Files/resources affected (optional)

Inputs: topic (required), action (required), summary (required), affects. Returns: Generic wrapper for non-object return types.

pool_statusB

Get multi-instance coordination pool status and recent activity.

Inputs: no named parameters. Returns: Generic wrapper for non-object return types.

project_statusA

Live MidOS system status + quick-start guide for your agent.

Call this anytime to get:

  • Real-time knowledge base stats (chunks, skills, EUREKA, truth patches)

  • Vector store health

  • Available MCP tools with usage examples

  • Research queue (pending topics)

  • Tips to get the most out of MidOS

This is your /status command. Use it to orient yourself and teach your agent how to leverage MidOS.

Inputs: no named parameters. Returns: Generic wrapper for non-object return types.

research_youtubeB

Queue a YouTube video for research. Midos will transcribe and extract insights.

Args: url: YouTube URL to research priority: Priority: 'high', 'normal', 'low'

Inputs: url (required), priority. Returns: Generic wrapper for non-object return types.

search_knowledgeC

Search the Midos knowledge base for relevant information.

Args: query: Search query (keywords or topic) max_results: Maximum results to return (default: 5)

Inputs: query (required), max_results. Returns: Generic wrapper for non-object return types.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 18 tools

    Disambiguation2/5

    Multiple tools have overlapping purposes. 'get_eureka', 'get_protocol', 'get_skill', and 'get_truth' all retrieve named documents with minimal distinction. Status tools like 'hive_status', 'memory_stats', 'pool_status', and 'project_status' also overlap, with 'project_status' subsuming many others. Additionally, a deprecated 'agent_bootstrap' adds confusion.

    Naming Consistency3/5

    Tool names are consistently in snake_case, but the pattern is mixed: some start with verbs (get_, list_, chunk_), others with nouns (agent_, episodic_, hive_). This inconsistency makes it harder for an agent to predict tool names, though they remain readable.

    Tool Count3/5

    With 18 tools, the server is on the higher end of the recommended range. While each tool has a distinct function, the count feels slightly heavy for a research protocol, especially given the overlaps. It could be streamlined.

    Completeness3/5

    The server covers onboarding, memory, knowledge retrieval, status monitoring, and research queuing, but lacks write operations for many document types (e.g., no create/update for skills, eurekas, or protocols). The research queue only has an enqueue tool, with no management or listing beyond status.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      B
      quality
      D
      maintenance
      Enables comprehensive Stacks blockchain development with 30+ specialized tools for Clarity smart contracts, SIP compliance, security analysis, and performance optimization. Provides complete access to SIP standards, token development templates, security-first patterns with mandatory post-conditions, and full-stack dApp development guidance.
      36
      7
      -
    • F
      license
      B
      quality
      Not graded
      maintenance
      Turns AI assistants into full-stack software engineers with 36 tools for cognitive reasoning, code validation, project scaffolding, and AI/IDE configuration generation across 130+ programming languages, databases, and frameworks.
      35
      13 npm
      -
    • A
      license
      A
      quality
      D
      maintenance
      Provides 634+ curated production-ready AI skills for any MCP-compatible client, covering areas like security, frontend, backend, infrastructure, AI/ML, and architecture. Enables AI agents to access best practices, patterns, and solutions across multiple domains.
      6
      1
      MIT