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.

Samgov

NPM · @PIPEWORX/MCP-SAMGOV · 2 COMPONENTS

SAM.gov MCP — Federal contract opportunities and entity registration data

+3 this week 81 Trust /100

Last scanned (9 hours ago)

Scores higher than 69% of npm servers

Category Finance and Payments

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
  • No install/post-install scripts declared.Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency97
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to pipeworx-io/mcp-samgov). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 0 days ago).Pass
  • Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability57
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 2015 tokens (~403/item across 5 items; 5 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 Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 6 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
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

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.

  • 5 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

  • 4 Nov 26 0
    • Stability: 0.17 → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • First check of Schema quality: unverified functional
    • Package version: 0.3.0 → 0.3.1 functional
  • 3 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 2 Nov 26 +1
    • Stability: unverified → 0.13 ▲ functional
  • 30 Oct 26 0
    • Security disclosure: unverified → fail ▼ functional
  • 29 Oct 26 78

    First indexed and scored.

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 5 Nov 2026 · Analysed npm/@pipeworx/mcp-samgov@0.3.1

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo pipeworx-io/mcp-samgov
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/pipeworx-io/mcp-samgov/.github/workflows/publish.yml@refs/heads/main
Rekor log index 3691893430
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:4d49123990a759f517f963a58b3fbb10a93b30106906137b721cd7bab847c33250f55811f8f662e9e6ebfc96aa33dc64e370c51642c7901f04d43091f

Background: How many MCP packages publish verified provenance →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 5 exposed · ~1,962 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
sam_entity_search ~426

Look up federal contractors registered in SAM.gov by business name, UEI, or CAGE code. Returns UEI, CAGE, legal and DBA name, address, NAICS and PSC codes, entity structure, registration and expiration dates, small-business/SBA certifications, and whether the entity carries an exclusion flag. Answers keyless from a local mirror of SAM.gov's public Entity Registration extract, ranking an exact UEI/CAGE/legal-name match above any fuzzy name hit and active registrations above expired ones. Every response carries a `mirror` field with the snapshot date and its age in days — the public entity extract is published MONTHLY, so an answer can legitimately be several weeks old; pass live:true with an API key when you need the registry as of today.

NameTypeReqDescription
_apiKeystring–Optional — omit it. This search answers keyless from the local snapshot of SAM.gov's public Entity Registration extract; a key is needed only for live:true.
active_onlyboolean–Only entities with an active registration (default false — expired registrations are returned but sorted below active ones).
business_namestringyesWhat to search for: a legal/DBA business name, or an exact UEI or CAGE code. Accepts query / q / name as aliases.
limitnumber–Number of results (1-100, default 10).
liveboolean–Force a live SAM.gov API lookup instead of the mirror. Needs _apiKey. Use only when you specifically need registrations changed since the mirror snapshot — the live entity API is capped at 10 request…
naicsstring–Filter by NAICS code (optional) — matches the primary NAICS or any NAICS the entity lists.
offsetnumber–Rows to skip for paging (default 0).
small_businessboolean–Filter to only small business entities (optional)
statestring–Filter by 2-letter US state code (e.g., "VA", "CA")

No output schema declared.

No examples provided.

sam_get_opportunity ~212

Get full details for a federal contract opportunity by solicitation number. Returns description, contact info, deadlines, attachments, NAICS codes, and set-aside status — the fields sam_search_opportunities does not carry. SAM.gov searches a posting-date range and caps it at one year: we resolve the solicitation's posting date automatically where we can and otherwise search the last year, so pass posted_from/posted_to only for an older solicitation.

NameTypeReqDescription
_apiKeystringyesSAM.gov API key — required. Free at https://sam.gov/content/entity-information; a key on an account with a SAM.gov role allows 1,000 requests/day.
posted_fromstring–Optional MM/DD/YYYY start of the posting-date window; only needed for a solicitation older than a year
posted_tostring–Optional MM/DD/YYYY end of the posting-date window
solicitation_numberstringyesThe solicitation number to look up (e.g., "N6133126R3101")

No output schema declared.

No examples provided.

sam_search_exclusions ~437

Search the SAM.gov Exclusions list — parties DEBARRED, suspended, or otherwise excluded from receiving federal contracts, grants, or assistance. Answers "is this company/person barred from federal contracting" for KYB / vendor-vetting / procurement due diligence. Filter by name, US state, and classification (Firm / Individual / Vessel / Special Entity). Returns each excluded party with the exclusion type, program, excluding agency, and active/termination dates. Distinct from OFAC sanctions (see sanctions_screen) — this is the federal procurement debarment list.

NameTypeReqDescription
_apiKeystring–Optional — omit it. This search answers keyless from the local snapshot of SAM.gov's public Exclusions extract, which is refreshed daily.
classificationstring–Optional classification: "Firm", "Individual", "Vessel", or "Special Entity Designation".
include_terminatedboolean–Accepted, but it currently changes NOTHING — SAM.gov's daily Exclusions extract carries only exclusions in force, so there are no terminated records for it to add. Measured 2026-09-13 over 400 sample…
limitnumber–Number of results (1-100, default 10).
namestring–Name to search (company or individual), e.g. "Smith Construction". Matched against the excluded party name; an exact UEI also matches. Optional if you pass `uei` instead — supply one of the two.
offsetnumber–Rows to skip for paging (default 0).
statestring–Optional 2-letter US state to filter by, e.g. "VA".
ueistring–Optional — check one specific UEI against the debarment list. More reliable than a name for KYB, since names collide and are transcribed inconsistently.

No output schema declared.

No examples provided.

sam_search_opportunities ~464

Search active federal contract opportunities by keyword, NAICS code (e.g., "541512"), set-aside type, posting date range, and procurement type. Searches SAM.gov's public Contract Opportunities extract, refreshed daily, without spending an API key — ranking matches by relevance with the opportunity TITLE weighted well above its description, so a genuine title hit outranks a notice whose boilerplate contract-clause text happens to mention the term. Returns titles, solicitation numbers, deadlines, and agencies, plus a `mirror` field reporting how fresh that snapshot is. SAM.gov requires a posting date range — if you omit posted_from/posted_to, we default to the last 30 days. Accepts query / q / keywords as aliases for keyword.

NameTypeReqDescription
_apiKeystring–Optional — omit it. This search answers keyless from the local snapshot of SAM.gov's public Contract Opportunities extract; a key is needed only to reach postings newer than that snapshot.
keywordstring–Search term for opportunity title or description. query, q, keywords accepted as aliases.
keywordsstring–Alias for keyword.
limitnumber–Number of results to return (1-100, default 10)
naicsstring–NAICS code to filter by (e.g., "541512" for computer systems design)
offsetnumber–Result offset for pagination (default 0)
posted_fromstring–Start of posting date range in MM/dd/yyyy format. Defaults to 30 days ago if omitted.
posted_tostring–End of posting date range in MM/dd/yyyy format. Defaults to today if omitted.
ptypestring–Procurement type filter: p (presolicitation), o (solicitation), k (combined synopsis/solicitation), a (award notice)
qstring–Alias for keyword.
querystring–Alias for keyword.
set_asidestring–Small business set-aside type: SBA (Small Business), SDVOSB (Service-Disabled Veteran), HUBZone, 8AN (8(a)), WOSB (Women-Owned), EDWOSB (Economically Disadvantaged Women-Owned)

No output schema declared.

No examples provided.

sam_set_aside_opportunities ~423

Find federal contract opportunities reserved for a specific class of small business — total or partial small business, 8(a), women-owned (WOSB/EDWOSB), HUBZone, service-disabled veteran-owned (SDVOSB), veteran-owned, Indian small business economic enterprise and Buy Indian. Answers "what HUBZone contracts are open", "recent 8(a) set-asides", "women-owned small business opportunities in NAICS 541512". Reads SAM.gov's public daily Contract Opportunities extract, so it costs no API key and works on the plain code (SBA, HZC, SDVOSBC, 8A, WOSB) or on the ordinary phrasing ("HUBZone", "women-owned", "8(a)", "service-disabled veteran"). Returns titles, solicitation numbers, deadlines, agencies and NAICS, with a `mirror` field reporting how fresh the snapshot is.

NameTypeReqDescription
_apiKeystring–Optional — omit it. This search answers keyless from the local snapshot of SAM.gov's public Contract Opportunities extract; a key is needed only to reach postings newer than that snapshot.
keywordstring–Optional keyword to narrow results
limitnumber–Number of results to return (1-100, default 10)
naicsstring–Optional NAICS code filter
set_asidestringyesSet-aside type (required). Either the SAM.gov code — SBA (total small business), SBP (partial), 8A, 8AN (8(a) sole source), WOSB, EDWOSB, HZC (HUBZone), HZS (HUBZone sole source), SDVOSBC, SDVOSBS, V…

No output schema declared.

No examples provided.

Install

How do I install the Samgov MCP server?

Samgov runs locally as an npm package, launched with npx -y @pipeworx/mcp-samgov. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @pipeworx/mcp-samgov

# add to Claude Code
claude mcp add pipeworx-io-samgov -- npx -y @pipeworx/mcp-samgov
Common questions

What is the Samgov MCP server?

Samgov is an MCP server listed in the public MCP registry as io.github.pipeworx-io/samgov. SAM.gov MCP, Federal contract opportunities and entity registration data. This page covers its npm package (@pipeworx/mcp-samgov).

Is the Samgov MCP server safe to use?

Samgov scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 Samgov MCP server expose?

Samgov exposes 5 tools: sam_search_opportunities, sam_get_opportunity, sam_entity_search, sam_set_aside_opportunities, sam_search_exclusions. Their descriptions and schemas cost roughly 1,962 tokens of context every time the server is loaded.

Is the Samgov MCP server still maintained?

Samgov is still listed as active in the MCP registry. We last reached this channel on 5 November 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 Samgov MCP server under?

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

What did VerifyMCP test on the Samgov MCP server?

VerifyMCP ran 16 checks on Samgov, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.