Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

GovCon API

PYPI · GOVCONAPI-MCP · SCANNED SEP 21

53 tools over US federal procurement: SAM.gov, FPDS awards, entities, subawards, exclusions.

Available components

+18 this week 76 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 0 of 29 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency45
Schema Quality & AI Usability65
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 13229 tokens (~249/item across 53 items; 53 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management70
  • Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 53 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 53 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the GovCon API MCP server?

GovCon API runs locally as a PyPI package, launched with uvx govconapi-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · govconapi-mcp

# add to Claude Code
claude mcp add govconapi-govconapi -- uvx govconapi-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "govconapi-govconapi": {
      "command": "uvx",
      "args": [
        "govconapi-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "govconapi-govconapi": {
      "command": "uvx",
      "args": [
        "govconapi-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add govconapi-govconapi -- uvx govconapi-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "govconapi-govconapi": {
      "type": "local",
      "command": [
        "uvx",
        "govconapi-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add govconapi-govconapi --command uvx --arg govconapi-mcp
# ~/.hermes/config.yaml
mcp_servers:
  govconapi-govconapi:
    command: "uvx"
    args: ["govconapi-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "govconapi-govconapi": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "govconapi-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add govconapi-govconapi -t stdio -c uvx -a govconapi-mcp
// mcp.json
{
  "mcpServers": {
    "govconapi-govconapi": {
      "command": "uvx",
      "args": [
        "govconapi-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 +15
    • Malware scan: unverified → pass security
  • 14 Sept 26 −14
    • Malware scan: pass → unverified security
  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

  • 7 Sept 26 +4
    • Stability: unverified → 0.23 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Sept 2026 · Analysed pypi/govconapi-mcp@0.2.3

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 29 packages
Packages resolved 29
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 53 exposed · ~13,229 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
search_recompetes ~521

Find contracts entering recompete within a window, a market read for NEW business (who else's contract is about to be up for grabs), and also useful post-award to watch your OWN contract's expiration (see get_recompete for the single-contract form of that). Capture & Teaming / Post-Award tool, Pro only, factual, never scored (no win-probability guess, just the facts: option runway, offer count, incumbent history). - naics: exactly 6 digits - agency: name substring - ends_after_months / ends_within_months: the window, e.g. 0-18 = "ending in the next 18 months," set ends_after_months higher (e.g. 6) to skip the too-late-to-influence band - date_anchor: current_end (next decision point) | potential_end (guaranteed recompete, all options used) - options_exhausted_only: true = only contracts whose options are ~exhausted (the high-confidence "must recompete" subset) - incumbent_excluded: true = only recompetes whose incumbent is CURRENTLY on the SAM exclusions list (can't legally win the recompete); false = only clean incumbents; omit for both - sort_by: ends_soonest | value | mod_churn | de_obligated Returns each row's `agency_code`/`sub_agency_code` alongside the published `agency`/ `sub_agency` names, and `award_id_piid`, pass that to get_recompete for the full incumbent-vulnerability read, or to get_contract/get_vehicle for the raw FPDS record. `incumbent_uei` is the same identifier every Capture/Teaming tool takes as `uei`. NOTE: get_recompete (the single-PIID detail form) does not yet carry agency_code/sub_agency_code, only this search does.

NameTypeReqDescription
agency
amount_max
amount_min
date_anchorstring
ends_after_monthsinteger
ends_within_monthsinteger
incumbent_excluded
limitinteger
naics
offsetinteger
options_exhausted_onlyboolean
set_aside
sort_bystring
state
NameTypeReqDescription
resultstringyes

No examples provided.

search_subawards ~312

Search FFATA subawards: who primes paid as subcontractors. Award & Compliance tool. For a single company's subs-paid or primes-that-paid-them reverse lookups, use get_prime_subawards / get_prime_relationships instead, narrower and simpler when you already have one UEI. - prime_uei / sub_uei: exact 12-char - piid: the PRIME contract's PIID - naics: exactly 6 digits - sub_name: substring, min 3 chars - limit: max 250 Data coverage starts FY2025 (~2024-10-01) and cannot go earlier on any plan, a `date_from` before that floor is silently clamped, not rejected; the response's `window` block (`clamped`, `earliest_searchable`, `reason`) discloses what actually ran. NOTE: this table has no `cage_code` field, you cannot CAGE-cross-check a subawardee through this tool, only by UEI/name.

NameTypeReqDescription
agency
amount_max
amount_min
date_from
date_to
limitinteger
naics
offsetinteger
piid
prime_uei
sort_by
sort_order
sub_name
sub_uei
NameTypeReqDescription
resultstringyes

No examples provided.

search_vehicles ~333

Search contract vehicles: IDIQs, GWACs, FSS schedules, BPAs, BOAs. Award & Compliance tool. Vehicles are long-lived and NOT limited to a rolling window the way prime-contract search is, a GWAC awarded years ago is still the vehicle you must hold today to compete for its orders. - uei/parent_uei: vehicle holder, exact 12-char - piid: vehicle PIID, exact - idv_type: IDC | FSS | BPA | GWAC | BOA - active_only: only vehicles whose period of performance hasn't ended - ceiling_min/ceiling_max: potential_total_value_of_award. A ceiling of `999999999999` (or `.99`) is FPDS's own placeholder for "no negotiated ceiling" (typical on GSA MAS/GWAC-style vehicles), not a literal dollar figure. - limit: max 250 Returns each vehicle's `award_id_piid`, pass to get_vehicle for detail or get_vehicle_holders (Pro) to see who holds it and who's actually earning through it.

NameTypeReqDescription
active_only
agency
ceiling_max
ceiling_min
date_from
date_to
idv_type
limitinteger
naics
offsetinteger
parent_uei
piid
sort_by
sort_order
uei
NameTypeReqDescription
resultstringyes

No examples provided.

search_wage_determinations ~296

Search Davis-Bacon (DBA), Service Contract Act (SCA), and CBA wage determinations by jurisdiction, number, or revision date. Bid & Proposal / Negotiate tool. For "which WDs apply where I'm bidding" use get_wds_by_location instead (the compliance shortcut); use this one when you need to browse/filter broadly or track revisions over time. - type: DBA | SCA | CBA - state: 2-letter US state code - county: substring - wd_number: substring (e.g. "AK2026", "1994-2371") - active_only: only currently-effective WDs - date_from/date_to: modified-date window, YYYY-MM-DD - construction_type: DBA only, Building | Heavy | Highway | Residential - sort_by: modified_date | publish_date | wd_number | revision_number - limit: max 100 Returns each WD's identifier, pass to get_wage_determination for the full classification/rate detail.

NameTypeReqDescription
active_onlyboolean
construction_type
county
date_from
date_to
limitinteger
offsetinteger
sort_by
sort_order
state
type
wd_number
NameTypeReqDescription
resultstringyes

No examples provided.

Common questions

What is the GovCon API MCP server?

GovCon API is an MCP server listed in the public MCP registry as io.github.govconapi/govconapi. 53 tools over US federal procurement: SAM.gov, FPDS awards, entities, subawards, exclusions. This page covers its PyPI package (govconapi-mcp).

Is the GovCon API MCP server safe to use?

GovCon API scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the GovCon API MCP server expose?

GovCon API exposes 53 tools: search_opportunities, get_opportunity, recent_changes, lookup_agency, check_exclusion, and 48 more. Their descriptions and schemas cost roughly 13,229 tokens of context every time the server is loaded.

Is the GovCon API MCP server still maintained?

GovCon API is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the GovCon API MCP server under?

GovCon API declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.