GovCon API

Search federal contracting data

search

Read-onlyIdempotent

Search one dataset. filters holds that dataset's filters; an unknown filter returns the full list. Agency values come from resolve(agency), NAICS codes from resolve(naics), UEIs from resolve(company). Dates are YYYY-MM-DD. (Pro) marks datasets that need the Pro plan. Keep limit small (20-50) and page with offset: rows are large. Only opportunities, forecasts and partners take keywords.

- opportunities: SAM.gov notices. naics, psc, agency, keywords, state, set_aside (HUBZone, WOSB, 8(a), Veteran,
  Small Business), notice_type (Solicitation, Combined Synopsis/Solicitation, Presolicitation, Sources Sought,
  Award Notice), posted_after, due_before, due_after, value_min, value_max;
  sort_by: posted_date | due_date | award_amount | title | agency | relevance
- opportunity_changes: notices added or changed since a time. since (ISO timestamp, required); no other filters
- forecasts: work agencies plan to buy. agency, naics, set_aside, state, est_award_fy, keywords, is_recompete,
  source (fco | dhs | hhs); sort_by: est_award_fy | est_solicitation_date | value_high | agency
- award_notices: SAM.gov award announcements. awardee, uei, naics, agency, value_min, value_max, date_from, date_to
- contracts: FPDS awards. naics, agency, uei, piid, award_type_code (A | B | C | D), date_from, date_to,
  amount_min, amount_max; sort_by: action_date | current_total_value_of_award | federal_action_obligation |
  recipient_name. Find a named vehicle's orders with parent_piid
- vehicles: IDIQs, GWACs, GSA Schedules. Needs one of uei, piid, agency, naics, idv_type (IDC | FSS | BPA |
  GWAC | BOA); active_only, ceiling_min. No name search: find a vehicle's PIID via contracts or the notice
- subawards: who subcontracts to whom. prime_uei, sub_uei, sub_name, naics, agency, piid, date_from, date_to,
  amount_min; sort_by: subaward_action_date | subaward_amount
- recompetes (Pro): contracts ending soon. naics, agency, set_aside, state, ends_within_months, amount_min;
  sort_by: ends_soonest | value | mod_churn | de_obligated
- companies (Pro): firms with award history, by name. q (name, REQUIRED), naics, agency, naics_small.
  Ranking firms without a name ("who wins this work") is partners
- entities: every SAM registration. q (name), naics, state, business_type (SAM code: "8W" WOSB, "QF" SDVOSB),
  naics_small (a NAICS the firm is SBA-small for), active_only
- expiring_registrations (Pro): SAM registrations about to lapse. within_days, state, naics
- partners (Pro): firms ranked by dollars won (FY2025 onward) in a NAICS, agency, state or PSC: who wins
  this work, the incumbents, teaming candidates. naics, agency, state, psc, keywords,
  set_aside (sdvosb | vosb | wosb | hubzone | 8a | sdb | minority_owned)
- protests: GAO bid protests. agency, protester, status (Open | Closed), outcome (Denied | Dismissed | Sustained |
  Withdrawn), filed_from, filed_to; sort: recent | oldest | filed | due
- exclusions: debarred or suspended parties. name, uei, cage_code
- wage_determinations: type (SCA | DBA | CBA), state (2 letters), county, wd_number, active_only
- wage_determinations_by_location: every determination for a place. state (2 letters, required), county, type
- offices: contracting offices that buy a NAICS. naics (required); sort: biggest | most_open

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "dataset": "<dataset>"
    },
    "name": "search"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No
`offset`	No
`dataset`	Yes
`filters`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 2, 2026

TDQS

A4.9/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnly/idempotent/openWorld annotations, it discloses plan gating ("(Pro) marks datasets that need the Pro plan"), performance constraints ("Keep `limit` small (20-50) and page with `offset`: rows are large"), and an edge behavior ("an unknown filter returns the full list"). It also flags required filters per dataset (e.g. `since` for opportunity_changes, `q` for companies), which the annotations do not cover.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The block is long, but the length is justified by a 17-way dataset dispatch and is front-loaded with "Search one dataset" followed by cross-cutting rules before per-dataset bullets. Density is high with little filler, though the format is a single large text blob rather than cleanly separated sections.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be explained; what remains — which dataset, which filters, which sorts, which require Pro, and pagination sizing — is fully specified. For a tool of this complexity with a 0%-documented schema, nothing an agent needs to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and `filters` is an open object, so the description must carry the full parameter burden — and it does, enumerating filter names and allowed values per dataset (set_aside options, notice_type values, award_type_code A|B|C|D, SAM business_type codes like "8W"/"QF", sort_by fields). It also documents the shared limit/offset semantics and required filters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource ("Search one dataset") and then enumerates all 17 datasets, each with a one-line characterization (e.g. "contracts: FPDS awards", "protests: GAO bid protests"). It also distinguishes itself from the resolve sibling by naming it ("Agency values come from resolve(agency)"), so an agent can place it precisely among siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit routing between datasets and alternatives: "Ranking firms without a name ('who wins this work') is partners", "No name search: find a vehicle's PIID via contracts or the notice", and "Only opportunities, forecasts and partners take keywords". These are concrete when-to-use / when-not-to-use statements, not implied guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All GovCon API tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.