Skip to content
MCP server

Phaedrus

Local research-feed server for literature-watch findings and draft-only revenue ideas

Runs locallyStatus and history
Pricing
Open source
Platforms
Linux, CLI, self-hosted
Runs
Locally
Version
1.0.0
Listing updated
3 days ago

About Phaedrus

Phaedrus is an open-source MCP server for knowledge and memory. It runs locally on your machine and is started by your AI client.

Phaedrus is a single Rust binary that works on plain files, with no database and no network listener. It speaks MCP over stdio and reads a data root holding a curated findings store, a watchlist and a scan inbox, set with --root or RESEARCH_ROOT.

Writes are narrow by design. research_submit files a candidate finding, roadmap item or test proposal into the scan inbox without touching the curated store. revenue_candidate_draft only drafts an opportunity_submit payload for lupin, a sister revenue-alignment server that owns its own ledger and is read-only from here. capability_context exposes lupin's capability registry as planning vocabulary.

It comes from Qompass AI. The release is an MCPB bundle for Linux x64 under Apache-2.0.

Install

Run in a terminal

claude mcp add phaedrus -- npx -y https://github.com/qompassai/phaedrus/releases/download/v1.0.0/phaedrus-mcp-1.0.0-linux-x64.mcpb

Add to claude_desktop_config.json

{
  "mcpServers": {
    "phaedrus": {
      "command": "npx",
      "args": [
        "-y",
        "https://github.com/qompassai/phaedrus/releases/download/v1.0.0/phaedrus-mcp-1.0.0-linux-x64.mcpb"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "phaedrus": {
      "command": "npx",
      "args": [
        "-y",
        "https://github.com/qompassai/phaedrus/releases/download/v1.0.0/phaedrus-mcp-1.0.0-linux-x64.mcpb"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "phaedrus": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "https://github.com/qompassai/phaedrus/releases/download/v1.0.0/phaedrus-mcp-1.0.0-linux-x64.mcpb"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "phaedrus": {
      "command": "npx",
      "args": [
        "-y",
        "https://github.com/qompassai/phaedrus/releases/download/v1.0.0/phaedrus-mcp-1.0.0-linux-x64.mcpb"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "phaedrus": {
      "command": "npx",
      "args": [
        "-y",
        "https://github.com/qompassai/phaedrus/releases/download/v1.0.0/phaedrus-mcp-1.0.0-linux-x64.mcpb"
      ]
    }
  }
}

Tools this server provides (7)

Taken from the project documentation; the running server may differ.

capability_context
Returns lupin's capability registry as planning vocabulary, optionally filtered.
feed_summary
Returns counts of findings by system and kind, systems watched and parse health.
finding_get
Returns one curated finding by id.
finding_list
Lists curated findings, optionally by system.
research_submit
Files a candidate into the scan inbox.
revenue_candidate_draft
Drafts an opportunity_submit payload for a revenue-shaped finding.
watchlist_list
Lists the watchlist of venues and terms.

What it does

Curated findings store
Reads individual findings or lists them by system.
Watchlist
Lists per-system venues and terms being watched.
Feed summary
Counts findings by system and kind and reports parse health.
Inbox submissions
Files candidates into the scan inbox without altering curated data.
Draft-only revenue seam
Drafts payloads for lupin and never writes its files.
File-based and offline
Runs as one binary over stdio with no database.

Good for

  • Review curated literature-watch findings for a system
  • Check which venues and terms are on the watchlist
  • Submit a candidate finding or test proposal for review
  • Draft a revenue opportunity from a finding

Pricing

Open source

Free; Apache-2.0

Prices change. Check qompass.ai before you buy.

Phaedrus FAQ

Does it need a database?

No. It works on plain files under a data root.

Can it modify the curated store?

No. research_submit only writes to the scan inbox.

What platforms are released?

The release bundle is built for Linux x64.

What licence applies?

Apache-2.0.

Is Phaedrus free?

Yes. Phaedrus is open source, so you can use and self-host it for free.

How do I add Phaedrus to Claude Code?

Run this command in your terminal: claude mcp add phaedrus -- npx -y https://github.com/qompassai/phaedrus/releases/download/v1.0.0/phaedrus-mcp-1.0.0-linux-x64.mcpb

What are the best alternatives to Phaedrus?

The closest alternatives to Phaedrus are Codebase Memory, XERJ, Agent-Native Analytics, Claude Code Ultimate Guide and Google Ads + Meta Ads + SEO/GEO MCP.

Alternatives to Phaedrus

  1. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  2. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  3. Open-source analytics app where an AI agent builds charts and dashboards from your data

    • Remote
    • Open source
    • 7.7K GitHub stars
    • Analytics and data
  4. MCP server for searching the Claude Code Ultimate Guide from any MCP client

    Runs locally
    • Open source
    • 6.5K GitHub stars
    • AI models and LLM tooling
  5. Hosted MCP connector for managing Google Ads, Meta Ads, GA4 and Search Console from chat

    • 8 tools
    • Remote
    • Freemium
    • 8.1K GitHub stars
    • Marketing and SEO
  6. Local-first long-term memory layer for AI agents, served over MCP

    Not checked yet
    • 5 tools
    • Remote
    • Open source
    • 1.3K GitHub stars
    • Knowledge and memory