MCP server for Gong.io - access calls, transcripts, and users
Nothing to run from here
FedWatch — Federal Funding & Lien Watcher is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
tool-list score
17
tools declared
remote
at its publisher
—
calls last 7d
What it does
Watches US federal contract and grant opportunities (SAM.gov, Grants.gov) and reports what changed.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http fedwatch-federal-funding-lien-watcher-mcp https://fedwatch-mcp.smatdesigns.workers.dev/mcp
# 2 — ask your agent for something these tools do
# fedwatch_signal_search, permits_search, licenses_search and 14 more
FedWatch — Federal Funding & Lien Watcher costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
JCAll 2 servers
jabbertones-cloud2 servers
2 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http fedwatch-federal-funding-lien-watcher-mcp https://fedwatch-mcp.smatdesigns.workers.dev/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
17 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Search multiple promoted public-data sources for the same organization/topic, normalize the records, rank actionability with a deterministic reason-bearing heuristic, and surface only conservative cross-source identity candidates. Scores are not probabilities and name matches are never called verified identity.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keyword | string | yes | Organization/topic name to search across promoted sources |
| source_ids | array | no | Optional promoted source ids; defaults to all currently searchable Wave 1 public-data sources |
| limit_per_source | integer | no | Maximum rows requested from each source before tier caps |
Search normalized public permit/violation records from a promoted official source. Promoted (2026-10-16 all-states expansion): Phoenix AZ (ArcGIS), Chicago permits + building violations, NYC DOB permits/violations + HPD violations, Austin permits + code cases, Los Angeles, San Francisco, Seattle, Honolulu, New Orleans, Kansas City, Orlando, Cincinnati (Socrata), and Philadelphia, Columbus, Charlot
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source_id | string | no | Source id; phoenix_current_permits (default) — see fedwatch_sources domain=permits for all promoted ids |
| keyword | string | no | Search permit name, company, address, description, scope, or permit number |
| status | string | no | Exact permit status, e.g. OPEN |
| company | string | no | Company/contractor name fragment |
| address | string | no | Street address fragment |
| permit_type | string | no | Permit type/description fragment |
| limit | integer | no | Maximum returned records (tier-capped; source max 2000) |
Search normalized public license records from promoted official sources. Arizona ADHS remains a partial provider-name search; California DCC remains a one-page partial search with unverified total/paging; New York OCM (jskf-tt3q) is an official statewide Socrata dataset whose exact filtered count, schema evidence, source refresh time and resumable paging are returned on every call — OCM rows are e
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source_id | string | no | Source id: azdhs_marijuana_facilities (default), ca_dcc_cannabis_licenses, ny_ocm_cannabis_licenses, or_olcc_cannabis_licenses, ct_cannabis_establishments |
| keyword | string | no | Facility/business/license/application fragment; at least 2 characters for ADHS, optional for the Socrata/API sources |
| status | string | no | CA/NY: exact upstream status or status code, e.g. 'Active' or 'LICACT'; OR/CT: exact license status |
| license_type | string | no | License type/code fragment, e.g. 'Retailer' or 'OCMRETL' |
| county | string | no | NY OCM only: exact county, e.g. 'Kings' |
| record_class | string | no | NY OCM only: active_license | expired_license | surrendered_license | cancelled_license | revoked_license | pending_application | proximity_protection | license_under_review | inactive_license |
| start_offset | integer | no | NY OCM only: row offset for an explicit resume. Any non-zero start is deliberately partial. |
| page_size | integer | no | NY OCM only: bounded page size, 1-1000 (default 500) |
| limit | integer | no | Maximum returned rows. Tier-capped for search; NY OCM supports explicit resume metadata when the exact filtered set is larger. |
Search normalized public business-register / new-filing records. PROMOTED (2026-10-16): ct_business_registry (Connecticut Business Master, 1.30M entities), or_business_registry (Oregon active businesses, 1.58M), pa_business_registry (Pennsylvania registered businesses, 4.17M), tx_franchise_taxpayers (Texas franchise-tax accounts incl. SOS file numbers, 3.49M) — all via the states' official Socrata
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source_id | string | no | Source id: ct_business_registry (default), or_business_registry, pa_business_registry, tx_franchise_taxpayers, co_business_entities / ny_business_filings (gated) |
| keyword | string | no | Entity name fragment |
| status | string | no | Exact entity status where the source publishes one (CT/OR; CO gated) |
| entity_type | string | no | Entity type filter (OR exact, PA/TX fragment; refused for CT) |
| county | string | no | PA: county name; NY (gated): county of principal office |
| filing_type | string | no | NY only (gated): exact filing type, e.g. 'ARTICLES OF ORGANIZATION' |
| formed_after | string | no | ISO date — only entities formed/registered after it (the new-business window) |
| limit | integer | no | Maximum returned records (tier-capped; source max 2000) |
Search SEC EDGAR filings. Source sec_edgar_filings (default): full-text search across filing text (keyword required) with optional form filter (e.g. 'D', '8-K', '13F-HR'), or a per-CIK submissions view when cik is given (recent-filings window — 13F coverage is that window only, labelled as such). EDGAR's own hit total is carried; when EDGAR reports it as a lower bound (relation gte) the response s
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source_id | string | no | Source id: sec_edgar_filings (default) |
| keyword | string | no | Full-text keyword/phrase searched across filing text |
| cik | string | no | CIK number — switches to the per-filer submissions view |
| form | string | no | Form filter, comma-separated, e.g. 'D' or '8-K,13F-HR' |
| limit | integer | no | Maximum returned records (tier-capped) |
Search FDA/CMS healthcare sources. openfda_drug_recalls (default): FDA drug enforcement/recall reports — keyword matches product description or recalling firm. openfda_device_510k: FDA 510(k) clearances — keyword matches device name or applicant. npi_registry: NPPES NPI registry — keyword is an organization-name prefix (city/state refine; an exact NPI goes in the apn field); phone numbers and auth
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source_id | string | no | Source id: openfda_drug_recalls (default), openfda_device_510k, or npi_registry |
| keyword | string | no | Keyword: product/firm (recalls), device/applicant (510k), organization name prefix (NPI) |
| status | string | no | Recalls only: exact FDA status, e.g. 'Ongoing' |
| city | string | no | NPI only: practice city |
| state | string | no | NPI only: practice state (2-letter) |
| apn | string | no | NPI only: exact 10-digit NPI number |
| limit | integer | no | Maximum returned records (tier-capped) |
Search Maricopa County Assessor parcel records (GIS Parcels layer) by APN, situs-address fragment, or subdivision/address keyword. Parcel identity, situs address, sale date/price, deed and subdivision only — owner name and mailing address exist in the layer and are deliberately never returned. TOOL SHAPE ONLY: recorder documents and tax delinquency are not this pack; delinquency data belongs to th
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source_id | string | no | Source id: maricopa_property_records (default) |
| apn | string | no | Assessor parcel number (APN or APN_DASH form) |
| address | string | no | Situs street-address fragment |
| keyword | string | no | Address or subdivision name fragment |
| limit | integer | no | Maximum returned records (tier-capped) |
Federal enforcement sources — currently ALL gated or planned, and the tools say exactly why per source: epa_echo (EPA ECHO DFR services documented but the documented calls did not reproduce from fleet egress on 2026-10-16 — adapter deferred, not faked), osha_enforcement (DOL API now requires a registered key; none is held and registration is an account creation), fcc_uls / faa_registry (bulk-file
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source_id | string | no | Source id: epa_echo (default), osha_enforcement, fcc_uls, faa_registry |
| keyword | string | no | Keyword (reserved for promoted adapters) |
| state | string | no | State filter (reserved) |
| zip | string | no | ZIP filter (reserved) |
| limit | integer | no | Maximum returned records (tier-capped) |
Court dockets via CourtListener/RECAP — GATED on the expansion's one named credential gap: CourtListener's API returns 401 without a token, no CourtListener credential exists in fleet stores, and account creation is out of scope for this server. Provisioning a COURTLISTENER_API_TOKEN secret is the exact unlock; until then calls return that named gate. PACER is never scraped.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source_id | string | no | Source id: courtlistener_dockets (default) |
| keyword | string | no | Docket/case keyword (reserved for the promoted adapter) |
| limit | integer | no | Maximum returned records (tier-capped) |
USPTO trademark/patent data — GATED on credential provisioning: the modern USPTO APIs (ODP, TSDR case status) all require a registered API key (keyless routes retired). The fleet holds a scoped USPTO ODP credential in its secure vault from the USIPE program; copying it into this Worker (secret USPTO_ODP_API_KEY, budgeted against the shared daily cap) is the named unlock. uspto_bulk is the keyless
| Parameter | Type | Required | Notes |
|---|---|---|---|
| source_id | string | no | Source id: uspto_odp (default) or uspto_bulk |
| keyword | string | no | Trademark/patent keyword (reserved for promoted adapters) |
| limit | integer | no | Maximum returned records (tier-capped) |
Search live federal contract opportunities on SAM.gov, newest-modified first. Filter by keyword, NAICS codes, set-aside codes (e.g. SBA, 8A, HZC, SDVOSBC, WOSB), and notice types (e.g. 'Sources Sought'). The public index applies those filters after fetch, so a filtered search pages deeper (up to 10 pages / 1,000 records) until the filter is satisfied — the response reports pages_fetched, how many
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keyword | string | no | Free-text keyword, e.g. 'janitorial' |
| naics | array | no | NAICS codes to require, e.g. ['561720'] |
| set_aside_codes | array | no | SAM set-aside codes to require |
| notice_types | array | no | Notice types to require, matched case-insensitively, e.g. ['Sources Sought'] |
| active_only | boolean | no | Only active notices (default true) |
| size | integer | no | Index records per page (1-100, default 100); also the post-filter target a filtered scan pages toward |
Search federal contract AWARDS already made (USASpending, served from FedWatch's relay-ingested copy — a fleet machine syncs USASpending daily because USASpending blocks direct Worker fetches): who won, how much, which agency, period of performance. Filter by keyword, NAICS, and/or agency; sort by amount (default) or most recent. Every response states its data-as-of and the true total_matches unde
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keyword | string | no | Keyword, e.g. a service or incumbent name |
| naics | array | no | NAICS codes |
| agency | string | no | Agency name fragment to require, e.g. 'Veterans Affairs' |
| sort | string | no | 'amount' (default, largest first) or 'recent' (newest obligation first) |
| days_back | integer | no | Award window in days (default 365) |
| limit | integer | no | Max results (default 25) |
Search PUBLIC, curator-ingested historical procurement results, disclosed winners, explicitly documented unsuccessful bidders, selection records and linked evidence. An award is never proof of which other firms lost or why. This is a partial curated KB, not all government procurements.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keyword | string | no | Case ID, title or agency keyword |
| agency | string | no | Exact agency name filter |
| category | string | no | Exact services/category filter |
| outcome | string | no | awarded | canceled | no_award | open | unknown |
| limit | integer | no | Maximum returned cases (tier-capped) |
Search nine source-linked historical PUBLIC procurement research cases: rubrics, committee scores, rankings, recommendations, approved awards and noncompetitive purchases. Preserves original stage; recommended/ranked is not awarded. This is a hand-selected research sample, NOT a complete bid universe or live SMAT outcomes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keyword | string | no | Search buyer, subject or procurement ID |
| stage | string | no | Filter observed stage, e.g. ranked_recommended, award_approved, committee_feedback |
| limit | integer | no | Maximum cases returned, tier-capped |
Search live federal grant opportunities on Grants.gov (posted by default). Returns hit count, agency, open/close dates, and assistance-listing (CFDA) numbers. Filter by agency code; sort by close date (soonest first); or restrict to grants closing within N days — sort/window apply to the fetched window and the response says when the window is narrower than the total hit count.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keyword | string | no | Keyword, e.g. 'water infrastructure' |
| status | string | no | posted | forecasted | closed | archived (default posted) |
| agency | string | no | Grants.gov agency code to require, e.g. 'EPA' |
| sort | string | no | 'close_date' for soonest deadline first (default: Grants.gov order) |
| closing_within_days | integer | no | Only grants whose close date falls within the next N days |
| rows | integer | no | Max results (default 25) |
Search the SAM.gov Assistance Listings program catalog (the programs behind the grants — by agency and program number). Catalog data: use grants_search for live deadlines.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keyword | string | no | Program keyword, e.g. 'rural health' |
| size | integer | no | Max results (default 25) |
Search tax-lien data. Default mode 'db': FedWatch's lien database (county lien records ingested from public sources; every hit is labeled with its source and extraction path) — filter by state, county, parcel, or free text matched against address/owner/parcel/city. For upcoming sales pass upcoming_only (sale date today or later) and/or sale_within_days, with sort 'sale_date_asc' for next-sale-firs
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mode | string | no | 'db' (default), 'nyc', 'discover', or 'both' (nyc + discover) |
| state | string | no | DB mode: state name or 2-letter abbreviation, e.g. 'New York' or 'NY' |
| county | string | no | DB mode: county name (partial match), e.g. 'Queens' |
| parcel | string | no | DB mode: exact parcel / APN id |
| upcoming_only | boolean | no | DB mode: only records whose sale date is today or later |
| sale_within_days | integer | no | DB mode: only sales within the next N days (implies upcoming) |
| sort | string | no | DB mode: 'sale_date_desc' (default) or 'sale_date_asc' (next sale first) |
| borough | string | no | NYC borough code 1-5 (1=Manhattan, 2=Bronx, 3=Brooklyn, 4=Queens, 5=Staten Island) |
| zip | string | no | NYC ZIP filter |
| query | string | no | DB mode: free text matched against address / owner / parcel / city. Discovery query for mode=discover, e.g. 'Cook County tax sale' or 'Florida tax lien' |
| limit | integer | no | Max results (default 25) |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install FedWatch — Federal Funding & Lien Watcher or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 96 / 100
Release 1.0.0 · scanned 28 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilityminimal
Coveragemanifest
Verificationnot in this report
Surface digestd3986d34440a376bc4388b90b4aecbfb28b159198aece4310f68008501c21970
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| fedwatch_signal_search | no tags | |
| permits_search | no tags | |
| licenses_search | no tags | |
| businesses_search | no tags | |
| securities_search | no tags | |
| healthcare_search | no tags | |
| property_search | no tags | |
| enforcement_search | no tags | |
| courts_search | no tags | |
| ip_search | no tags | |
| contracts_search_opportunities | no tags | |
| contracts_search_awards | no tags | |
| contracts_search_bid_outcomes | no tags | |
| contracts_search_bid_research | no tags | |
| grants_search | no tags | |
| grants_search_programs | no tags | |
| liens_search | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestd3986d34440a376b
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
1.0.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish FedWatch — Federal Funding & Lien Watcher can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.