govcon-recompete

Predict federal contract recompetes: expiring contracts, likely competitors, win odds.

Should I use this

Quality & Safety

A
Description quality
90%
Schema completeness
88%
Naming quality
80%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (1)

  • LOWTool 'lane_competitors' description lacks action verbin lane_competitors

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~496Tokens (tool definitions)
~1.1 KBTypical response size
Minimal attention impact (0.39% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "govcon-recompete": {
      "url": "https://recompete.dropwatchhq.com/mcp"
    }
  }
}

Remote endpoints

https://recompete.dropwatchhq.com/mcpstreamable-http

What it can do

Tool inventory

Tools (3)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
⚪predict_recompete(gid, naics, incumbent, agency, topN)

Predict WHO will win an expiring federal contract recompete. Pass a contract identifier (USAspending generated_internal_id / award gid) OR a NAICS+incumbent pair. Returns the incumbent with an adjusted incumbent-advantage probability plus top likely competitors ranked by recent award velocity in the NAICS/agency lane, the BASE RATES used, sample size, and an honest confidence band. Probabilistic estimate from PUBLIC USAspending data — not insider info.

Input Schema

{
  "type": "object",
  "properties": {
    "gid": {
      "type": "string",
      "description": "USAspending generated_internal_id (award gid). Best input."
    },
    "naics": {
      "type": "string",
      "description": "6-digit NAICS, used to build the competitor field (required if no gid)."
    },
    "incumbent": {
      "type": "string",
      "description": "Incumbent contractor name (required if no gid)."
    },
    "agency": {
      "type": "string",
      "description": "Awarding agency name (optional, sharpens the lane)."
    },
    "topN": {
      "type": "number",
      "description": "Number of competitors to return (default 5)."
    }
  }
}
🟢expiring_recompetes(naics, agency, minDays, maxDays, minAmount, ...)

List federal contracts EXPIRING in a horizon window (period-of-performance end), with a winner prediction for each. Filter by NAICS and agency. This is the recompete pipeline feed.

Input Schema

{
  "type": "object",
  "properties": {
    "naics": {
      "type": "string",
      "description": "6-digit NAICS."
    },
    "agency": {
      "type": "string"
    },
    "minDays": {
      "type": "number",
      "description": "Window floor in days (default 90)."
    },
    "maxDays": {
      "type": "number",
      "description": "Window ceiling in days (default 180)."
    },
    "minAmount": {
      "type": "number",
      "description": "Minimum award $ (default 1,000,000)."
    },
    "limit": {
      "type": "number",
      "description": "Max contracts (default 20)."
    }
  }
}
⚪lane_competitors(naics, agency, limit)

Return the firms with the most recent award velocity in a NAICS (and optional agency) lane — i.e. the likely bidders on any recompete in that lane, ranked by recent wins and dollars.

Input Schema

{
  "type": "object",
  "properties": {
    "naics": {
      "type": "string"
    },
    "agency": {
      "type": "string"
    },
    "limit": {
      "type": "number",
      "description": "Default 15."
    }
  },
  "required": [
    "naics"
  ]
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded3 tools
verifiedversion not recorded3 tools
verifiedversion not recorded3 tools