BidCatch MCP server

• Registry nameco.bidcatch/bidcatchverified in the MCP registry

The registry name sits under bidcatch.co. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-22
• Tools8
• Server calls itselfbidcatch
• Server version1.1.0
• Protocol version2025-06-18

On 2026-10-22 the server answered initialize and tools/list without a sign-in. First answer in 195 ms.

• Its tools do every use case we checked: find open government bids matching your industry codes; check who won past federal contracts and at what value; track federal contracts nearing expiry before their rebid.
• Checked on 1 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
• What an agent can do with it3 of 3 use cases
• Answeredmeasuring1 of the 7 daily checks it takes to print a share
• Median first answer293 ms
• Space in an agent's context≈ 1,520 tokensthe definitions of all its tools (8), which an agent carries on every turn
• Tool definitionsB · 79 of 100
• Typed results0 of 8 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 2 of 8
• Not saying whether it only reads or can destroy: 8 of 8

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• search_bids

  Search government bid opportunities (open and past) by keyword, state, and buyer level. Results are relevance-ranked; keyword matches in the title outrank passing mentions in the description.

• get_award_history

  Search federal contract award history — who won what, for how much, and when. Use it to size up incumbents, price work, or find buyers. Requires a BidCatch intel key.

• get_recompete_radar

  List federal contracts nearing expiration — each one a competition about to reopen. Filter by keyword, NAICS code, or state. Requires a BidCatch intel key.

• get_agency_forecast

  List an agency's published procurement forecast — planned contract actions with estimated values and timelines, in the agency's own words. Planning-grade data; entries can be revised or cancelled. Requires a BidCatch intel key.

• get_protest_record

  Search Government Accountability Office (GAO) bid protest decisions — who challenged an award, and whether the referee sustained or denied it. Requires a BidCatch intel key.

• check_exclusions

  Check SAM.gov's exclusion (debarment) list for a company or person — entities the government has barred from receiving federal contracts or subcontracts. Run this before teaming with or subcontracting to anyone: one excluded partner can…

• find_teaming_partners

  Find who a company teams with on federal contracts — the primes it subcontracts for and the subcontractors under it. Built from prime-reported subcontract records (USAspending/FSRS): real reported relationships, not guesses. Use it before…

• search_awards

  Filter federal contract awards by exact fields — recipient, awarding agency, NAICS code, state — instead of keyword search. Includes a single-bid filter for awards that drew exactly one offer. Use this when you know the slice you want…