GovCon API MCP
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GOVCONAPI_KEY | Yes | Your GovCon API key. Must start with 'gca_' (e.g., gca_your_key_here). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| resolveA | Turn what the user said into the IDs and codes the other tools take. Start here when the user names an agency, describes their work, or names a company.
|
| searchA | Search one dataset.
|
| getA | Fetch one record by its ID. IDs come from search results or resolve. (Pro) needs the Pro plan.
|
| marketA | How big a NAICS market is, who wins it, and how it buys, across every agency. A 6-digit
|
| priceA | Price evidence for a bid. (Pro) needs the Pro plan.
|
| contactA | Who to talk to. Both need the Pro plan.
|
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
The six tools have genuinely distinct roles: resolve maps names to IDs, search queries datasets, get fetches single records, and market/price/contact are analytics or people lookups. The descriptions actively disambiguate known overlap points (resolve(company) vs search(companies) vs get(entity); market/price vs search(contracts) with agency filters), though the heavy sub-action multiplexing inside each tool still leaves room for misselection between e.g. search(recompetes) and search(contracts) with date filters.
All six top-level tools are single lowercase words with no camelCase/snake_case mixing, which is predictable and readable. There is a minor stylistic split between verbs (resolve, search, get) and nouns (market, price, contact), and the sub-actions inside each tool follow a separate snake_case convention, but this is disclosed and consistent within itself.
Six tools is a well-scoped count for a broad federal procurement data API, and each dispatcher earns its place as a coherent category rather than a redundant wrapper. The tradeoff is that the real surface is 40+ sub-operations crammed into tool parameters, which is a lot of hidden complexity for six entries, but it is deliberate and documented.
Coverage is unusually broad for the domain: opportunities, forecasts, awards/FPDS, vehicles, subawards, recompetes, entities, exclusions, protests, wage determinations, market analytics, pricing benchmarks, labor rates and contacts. Gaps are minor — read-only by design, and there is no direct path from an opportunity to its Q&A/amendment history or a teaming/JV construct beyond partners and prime_subawards.