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.

Fac

NPM · @PIPEWORX/MCP-FAC · 2 COMPONENTS

Federal Audit Clearinghouse (FAC) MCP — US single-audit data, served from a served from a…

+4 this week 82 Trust /100

Last scanned (9 hours ago)

Scores higher than 72% 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-fac). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 3 days ago).Pass
  • Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability61
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 2415 tokens (~345/item across 7 items; 7 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 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 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.

  • 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.

  • 1 Nov 26 +1
    • Stability: 0.07 → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Tool coverage: 100 → unverified ▼ functional
    • Capabilities: pass → unverified ▼ functional
    • First check of Schema quality: unverified functional
    • Package version: 0.2.0 → 0.2.1 functional
  • 30 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 0 to 3. That category is still filling its 30-day observation window: 0 days of observed history at the previous scan, 1 at this one. The score rises as the window fills, whether or not the server changes.

  • 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-fac@0.2.1

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-fac
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/pipeworx-io/mcp-fac/.github/workflows/publish.yml@refs/heads/main
Rekor log index 3635935450
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:efce6d8a5ac1cbc70bf32f036526a5e83f159563e5cb4f6715511b10f381ed786cd78dd186f4d94de42bc2f82b7c3946befa8b97088c1b9225a7c01e5

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 · 7 exposed · ~2,364 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
fac_audit_findings ~244

Audit findings recorded against single audits — the compliance exceptions, material weaknesses, significant deficiencies, questioned costs and repeat findings that auditors reported. Query by report_id, or by recipient name/UEI to sweep every audit that recipient filed. Answers "has this grant recipient had audit findings, and were they material or repeated".

NameTypeReqDescription
audit_yearnumber–Restrict the resolved audits to one audit year (used with auditee_name or uei).
auditee_namestring–Recipient name substring; the tool resolves matching audits first, then their findings. Aliases: query, q, name.
include_textboolean–Also attach the narrative finding text when FAC recorded any (default false — the text rows are long; a pre-2022 migrated audit often has none on file).
limitnumber–Max finding rows to return, 1-200 (default 50).
report_idstring–FAC report id to pull findings for. Aliases: id, audit_id.
ueistring–Recipient UEI; resolves that recipient's audits, then their findings. Alias: auditee_uei.

No output schema declared.

No examples provided.

fac_cross_table_screen ~378

Screen single audits across state, federal program (CFDA), and finding type / material weakness in ONE call — a join FAC's own live API cannot express (its PostgREST has no foreign key between /general, /federal_awards and /findings). Answers compound diligence questions like "material weaknesses in Texas under CFDA 93.224" or "questioned-cost findings on highway funding (20.205) over $1M". Every filter is optional; pass at least one to keep the result meaningful. Returns one row per matching (audit, award, finding) combination, ranked by award dollar amount.

NameTypeReqDescription
audit_yearnumber–Restrict to one audit year.
cfdastring–Assistance Listing / CFDA number, e.g. "93.224" or a bare 2-digit agency prefix "93". Aliases: program_number, assistance_listing, program, cfda_number.
federal_agency_prefixstring–Two-digit agency prefix on its own. Alias: prefix.
federal_award_extensionstring–Program extension on its own, e.g. "224". Alias: extension.
finding_typestring–Substring match on FAC's finding type_requirement code (e.g. "A" internal control, "B" allowable costs — FAC packs several letters into one field, so this matches loosely).
limitnumber–Rows to return, 1-100 (default 25).
material_weakness_onlyboolean–Only findings flagged as a material weakness.
min_amountnumber–Only award rows expending at least this many dollars.
offsetnumber–Rows to skip, for paging.
statestring–2-letter auditee state code, e.g. "TX".

No output schema declared.

No examples provided.

fac_federal_awards_by_program ~345

List the organizations that expended money under a given federal Assistance Listing / CFDA number (e.g. "93.224" community health centers, "84.010" Title I, "20.205" highway planning), ranked by dollars expended, with the recipient name, state, audit year and whether it was a major program. Answers "who spends the money in this federal grant program and how much does each one run".

NameTypeReqDescription
audit_yearnumber–Restrict to one audit year, e.g. 2023.
cfdastring–Assistance Listing / CFDA number. Accepts "93.224", "93-224", "93 224", "93224", or a bare agency prefix "93" for every program at that agency. Aliases: program_number, assistance_listing, program, c…
federal_agency_prefixstring–Two-digit agency prefix on its own, e.g. "93" for HHS. Alias: prefix.
federal_award_extensionstring–Program extension on its own, e.g. "224". Alias: extension.
include_recipientsboolean–Resolve each report_id to the recipient name and state (default true; one extra local query).
limitnumber–Rows to return, 1-200 (default 25).
major_onlyboolean–Keep only programs audited as major programs.
min_amountnumber–Only rows expending at least this many dollars.
statestring–2-letter recipient state code to narrow the ranking, e.g. "TX".

No output schema declared.

No examples provided.

fac_findings_search ~344

Full-text search over audit finding NARRATIVES — the actual prose auditors wrote describing a compliance exception ("failed to submit the Federal Single Audit report within the timeframe prescribed", "total available cash was less than total advances from grantors"). This is not possible against the live FAC API, which exposes no cross-table join; it is what searching the underlying text directly unlocks. Optionally narrow by state, audit year, CFDA agency prefix, or material-weakness-only. Narrative text is only on file for more recent filings — audits migrated from the pre-2022 Census-run FAC often have none, and rows without text are simply not returned rather than shown blank. Answers "which audits mention X in their findings", e.g. "data security", "cash management", "timesheet".

NameTypeReqDescription
audit_yearnumber–Restrict to one audit year.
federal_agency_prefixstring–Restrict to findings on awards under this 2-digit agency prefix (e.g. "93" for HHS). Alias: cfda_prefix.
limitnumber–Rows to return, 1-100 (default 25).
material_weakness_onlyboolean–Only findings flagged as a material weakness.
offsetnumber–Rows to skip, for paging.
querystringyesSearch phrase, e.g. "data security" or "questioned costs travel". Uses PostgreSQL websearch syntax (quote a phrase, "-word" to exclude). Aliases: q, text.
statestring–2-letter auditee state code to narrow the search, e.g. "TX".

No output schema declared.

No examples provided.

fac_get_audit ~254

Fetch one single audit by its FAC report_id (e.g. "2025-09-GSAFAC-0000422512"), including its summary_url — the official Federal Audit Clearinghouse dissemination summary page for that report — enriched with the full federal program detail: every Assistance Listing (CFDA) number the entity expended money under, the program name, dollars expended per program, whether it was audited as a major program, and the opinion type. Also returns the auditor firm and audit findings when FAC recorded any. Does NOT return named-individual contact details (auditee/auditor contact name, email, phone) — those are not carried here; see the report's summary_url on fac.gov for that. Answers "what did this specific audit cover and what did it conclude".

NameTypeReqDescription
award_limitnumber–Max federal award rows to include, 1-500 (default 200).
include_findingsboolean–Attach audit findings for this report (default true).
report_idstringyesFAC report id as returned by fac_search_audits, e.g. "2025-09-GSAFAC-0000422512". Aliases: id, audit_id.

No output schema declared.

No examples provided.

fac_recipient_audit_history ~210

Year-by-year single-audit history for one grant recipient, identified by UEI or by name. Returns each audit year with total federal awards expended, the report_id, the oversight agency and the FAC acceptance date, plus a growth read on the spend trend. Answers "how has this organization's federal funding moved over time and which years were audited".

NameTypeReqDescription
auditee_namestring–Recipient name substring when the UEI is unknown, e.g. "johns hopkins". Aliases: query, q, name.
einstring–Employer Identification Number, an alternative exact identifier. Alias: auditee_ein.
statestring–2-letter state code, useful to disambiguate a common name.
ueistring–SAM.gov Unique Entity Identifier, the precise way to pin one recipient. Alias: auditee_uei.
yearsnumber–Max audit years to return, 1-40 (default 15).

No output schema declared.

No examples provided.

fac_search_audits ~589

Search US single audits (Uniform Guidance / former OMB A-133) filed with the Federal Audit Clearinghouse — "the FAC" — by auditee name, UEI, EIN, state, ZIP code, audit year, or minimum federal dollars expended. Covers every kind of non-federal recipient: cities, towns, counties, school districts, fire and water districts, housing authorities, universities, tribes, hospitals and nonprofits. Returns the report_id, summary_url (the official FAC dissemination summary page for that submission), the organization name, city, state and ZIP on file, total federal awards expended for the year, the cognizant/oversight agency, and the date FAC accepted the submission. Puerto Rico municipalities are found under either their Spanish or English legal name. Answered without a live api.data.gov key or its rate limit. Answers "does this grant recipient file a single audit and how much federal money does it run", and "what is the FAC report ID / summary URL for this entity".

NameTypeReqDescription
ascendingboolean–Sort ascending instead of descending.
audit_yearnumber–Fiscal audit year, e.g. 2023.
audit_year_minnumber–Earliest audit year to include.
auditee_namestring–Organization name, matched as a forgiving case-insensitive substring (e.g. "stanford", "county of los angeles"). A municipality name is searched in both languages FAC files under, so "MUNICIPIO DE BA…
einstring–Employer Identification Number, digits only, exact match. Alias: auditee_ein.
limitnumber–Rows to return, 1-200 (default 20).
min_total_expendednumber–Only audits whose total federal awards expended is at least this many dollars (e.g. 100000000 for billion-dollar-scale recipients).
offsetnumber–Rows to skip, for paging.
order_bystring–Sort column, descending by default. Defaults to total_amount_expended.
statestring–2-letter auditee state code (e.g. "CA"). Alias: auditee_state.
ueistring–SAM.gov Unique Entity Identifier (12 chars), exact match. Alias: auditee_uei.
zipstring–Auditee ZIP code, matched on the 5-digit prefix so it works against both the 5-digit and 9-digit forms FAC stores ("75082", "009601588"). An auditee's ZIP on file changes between filing years; if it…

No output schema declared.

No examples provided.

Install

How do I install the Fac MCP server?

Fac runs locally as an npm package, launched with npx -y @pipeworx/mcp-fac. 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-fac

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

What is the Fac MCP server?

Fac is an MCP server listed in the public MCP registry as io.github.pipeworx-io/fac. Federal Audit Clearinghouse (FAC) MCP, US single-audit data, served from a served from a… This page covers its npm package (@pipeworx/mcp-fac).

Is the Fac MCP server safe to use?

Fac scores 82 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 Fac MCP server expose?

Fac exposes 7 tools: fac_search_audits, fac_get_audit, fac_audit_findings, fac_federal_awards_by_program, fac_recipient_audit_history, and 2 more. Their descriptions and schemas cost roughly 2,364 tokens of context every time the server is loaded.

Is the Fac MCP server still maintained?

Fac 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 Fac MCP server under?

Fac 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 Fac MCP server?

VerifyMCP ran 16 checks on Fac, 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.