Skip to content
SpendQuery logo

SpendQuery MCP server

Which MCP servers are SpendQuery's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-29

← Back to SpendQuery

Whose server it is
  • Registry namecom.spendquery/spendqueryverified in the MCP registry

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

When we asked itchecked 2026-10-29
  • Stateanswerschecked 2026-10-29
  • Tools13
  • Server calls itselfSpendQuery
  • Server version0.3.0
  • Protocol version2025-06-18

On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 344 ms.

Should an agent connect itNot proven either way yet
  • Its tools do score open bids against your company's fit, but not receive alerts for government bids matching your company.
  • Checked on 6 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.

Measured dailydaily checks: 6, the first on 2026-10-29
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
  • What an agent can do with it1 of 2 use cases
  • Answeredmeasuring6 of the 7 daily checks it takes to print a share
  • Median first answer458 ms
  • Space in an agent's context≈ 3,338 tokensthe definitions of all its tools (13), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 13 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • cannot · receive alerts for government bids matching your company
  • can do · score open bids against your company's fit
  • not sure · compare federal contract spending across states and counties

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

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 (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). 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 →

Tools it offers13 tools · read 2026-10-29
  • get_catalog

    What SpendQuery can answer: data coverage, metrics, dimensions (with examples and whether they apply to contracts or assistance), analyses, the QueryPlan JSON schema, planning rules and example question -> plan pairs. Call this first (no…

  • run_plan

    Run a QueryPlan (see get_catalog.plan_schema). Returns status (ok | clarify | unsupported | error), a one-paragraph answer, columns, rows (max 100), the SQL that ran, caveats and how names were resolved to codes.

  • search_codes

    Look up codes and official names. kind: agency | bureau | state | county | naics | psc | program. Matches names (substring, case-insensitive) or code prefixes. Plans can use either the names or the codes.

  • search_recipients

    Find award recipients (companies, universities, governments) by name or UEI. Returns each registration's UEI, parent, listed-company ticker (if matched) and its OWN obligations across loaded years, largest first. A parent's money sits on…

  • browse_codes

    Browse what the government buys, with contract spend. kind: psc (products and services) | naics (industries). No group and no query -> the groups (PSC: services by letter, e.g. D = IT services, R = professional support; products by 2…

  • get_notice

    One SAM.gov contract notice as SpendQuery's brief sees it, no AI: the decision card (what the buyer needs, blockers, unknowns, a next step; each line labelled record / files / unknown), the timeline of the buy (planned buy, the contract…

  • size_standard

    SBA small business size standards (13 CFR 121.201, the eCFR table): a NAICS code, a code prefix (5415) or industry words -> receipts ($ millions) or employees, exceptions and footnotes, and the programs that use them.

  • naics_finder

    Describe the work in plain words -> the NAICS codes buyers actually use for it (codes on SAM.gov notices whose titles have the words and on federal contracts described with them), each with its SBA size standard.

  • vehicle_match

    For 6-digit NAICS codes (and an optional agency): the shared contract vehicles (GWACs, multiple-award IDIQs, GSA Schedule, BPAs) carrying last complete year's contract money in those codes, the share through each and who each is reserved…

  • search_far

    Search the FAR and the DFARS (48 CFR chapters 1 and 2, as codified in the eCFR): sections whose title or text has every word, or a section number (e.g. 52.219-14) straight to it. reg: FAR | DFARS to limit. Returns section numbers, titles…

  • get_far_section

    One FAR or DFARS section's full text (paragraphs), its part and subpart, the sections it refers to and the ones referring to it, and Federal Register rules changing its part. Cite it as FAR <section> (or DFARS) with the as-of date in…

  • search_local_bids

    State, county and city government bids and contracts (not federal awards), from the governments that publish them as open data: Los Angeles (the City, LA County, LADWP, LAUSD, airports, port, Metro), New York City, San Francisco…

  • sbir_awards

    SBIR and STTR awards since 1983 from SBA's SBIR.gov records, and who received them: totals, awards by year (Phase I / II), by agency, the companies with the most, and the latest awards (company, title, agency, phase, amount, year)…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "spendquery": {
      "type": "http",
      "url": "https://api.spendquery.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http spendquery https://api.spendquery.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://api.spendquery.com/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.