# Panda Public Funding Tools (pypi · panda-public-funding-tools)

Public money & safety: grants, contracts, SAM.gov bids, SBIR, SEC, FedReg, recalls, EU tenders (10).

- Trust score: 68/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- pypi · `panda-public-funding-tools`: 68/100 (this document), [markdown](https://verifymcp.io/servers/pandadad0214-panda-public-funding-tools/panda-public-funding-tools.md), [page](https://verifymcp.io/servers/pandadad0214-panda-public-funding-tools/panda-public-funding-tools)

## Channel facts

- Registry: `pypi`
- Package: `panda-public-funding-tools`
- Version: `0.2.0`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 1 of 31 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to pandadad0214/panda-public-funding-tools).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 10 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 57/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 10110 tokens (~1011/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Panda Public Funding Tools MCP server?

Panda Public Funding Tools runs locally as a PyPI package, launched with uvx panda-public-funding-tools. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add pandadad0214-panda-public-funding-tools -- uvx panda-public-funding-tools
```

### Cursor

```json
{
  "mcpServers": {
    "pandadad0214-panda-public-funding-tools": {
      "command": "uvx",
      "args": [
        "panda-public-funding-tools"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "pandadad0214-panda-public-funding-tools": {
      "command": "uvx",
      "args": [
        "panda-public-funding-tools"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add pandadad0214-panda-public-funding-tools -- uvx panda-public-funding-tools
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "pandadad0214-panda-public-funding-tools": {
      "type": "local",
      "command": [
        "uvx",
        "panda-public-funding-tools"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add pandadad0214-panda-public-funding-tools --command uvx --arg panda-public-funding-tools
```

### Hermes

```yaml
mcp_servers:
  pandadad0214-panda-public-funding-tools:
    command: "uvx"
    args: ["panda-public-funding-tools"]
```

### Netclaw

```json
{
  "McpServers": {
    "pandadad0214-panda-public-funding-tools": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "panda-public-funding-tools"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add pandadad0214-panda-public-funding-tools -t stdio -c uvx -a panda-public-funding-tools
```

### Other

```json
{
  "mcpServers": {
    "pandadad0214-panda-public-funding-tools": {
      "command": "uvx",
      "args": [
        "panda-public-funding-tools"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 68, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-20 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 82, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-11-17 (score 66, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-16 (score 81, +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.

### 2026-11-15 (score 80, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-14 (score 65, −14)

- [security regression] Malware scan: pass → unverified

### 2026-11-12 (score 79, +15)

- [security improvement] Malware scan: unverified → pass

## MCP tools (10)

### `grants_finder` (~1208 tokens)

Grants.gov Scraper: Federal Grants, NIH & NSF Awards API

Search US federal funding in one call: open and forecasted Grants.gov opportunities plus already-funded NIH RePORTER and NSF awards, one row per grant with agency, dates, amount (USD), eligibility and link. Unlike sbir_sttr_topic_radar (SBIR/STTR solicitation topics with deadlines and DoD Q&A) and federal_contract_finder (procurement contracts on USAspending), this covers assistance grants and research awards. Use when you need grants to apply for or want to see who was funded for a topic. Do not use for contracts (use federal_contract_finder) or small-business R&D topics (use sbir_sttr_topic_radar). Parameters: sources picks the mix; grants_gov is apply-able funding, nih/nsf are past awards. maxResultsPerSource applies to each source, so worst-case billed rows = maxResultsPerSource x number of sources; run_max_items does not set it, so keep it small first and rely on run_max_charge_usd. minAmount drops rows whose source publishes no amount. includeGrantsGovDetails adds award ceiling and eligibility but slows the run; turn it off for quick scans. Returns per item: agentSummary, source, recordType, status, title, agency, number, openDate, closeDate, amount, eligibility, summary, url.

Behavior: read-only; runs the Apify Actor pandadad0214/grants-finder (https://apify.com/pandadad0214/grants-finder) on your own Apify account. Price: $0.003 per grant found. Runs that find nothing are not charged per result, and spending is capped per call by run_max_charge_usd (default $0.50). run_max_items (default 50) limits items returned but does not limit what the Actor bills; use the tool's own limits and run_max_charge_usd. Most calls finish in 5-15 s for a few inputs; large inputs or crawls can take minutes, so raise run_timeout_secs (max 300) or shrink the input after a timeout error. Returns JSON {actor, count, items}; long text output is trimmed to whole items, with all items in structuredContent.

Input parameters:

- `agencies` (array): Agencies. Optional. Grants.gov agency codes or names (HHS-NIH11, NSF, DOE, USDA, ED, Geological Survey; a code prefix like HHS matches all HHS sub-agencies). NIH institutes (NCI, NIAID, NIMH… or NIH…
- `dateFrom` (string): From date. Optional. 2025, 2025-06 or 2025-06-30. Applies to the Grants.gov posted date, the NIH project start date and the NSF award date.
- `dateTo` (string): To date. Optional. 2026, 2026-12 or 2026-12-31.
- `grantsGovFundingCategories` (array): Grants.gov funding categories. Optional Grants.gov category codes, e.g. ST (science and technology), HL (health), ED (education), AG (agriculture), ENV (environment), CD (community development).
- `grantsGovStatuses` (array): Grants.gov opportunity status. Default: forecasted and posted (still open or coming soon).
- `includeGrantsGovDetails` (boolean): Grants.gov details (amount, eligibility, summary). Fetch each opportunity's detail page for award ceiling, eligibility and summary. Turn off for a faster title-and-deadline list. Default: on.
- `keywords` (string, required): Keywords. What the funding is for, e.g. artificial intelligence, rural broadband, opioid prevention. Use quotes for exact phrases ("machine learning"). NIH also understands AND / OR / NOT.
- `maxAmount` (integer): Maximum amount (USD). Optional. Whole number, 0 or more USD.
- `maxResultsPerSource` (integer): Maximum results per source. You pay per returned result, so this also caps the cost. Up to 1,000 per source. Whole number, 1 to 1,000 results per source; default 50.
- `minAmount` (integer): Minimum amount (USD). Optional. Grants.gov award ceiling, NIH fiscal-year award or NSF estimated total. When set, rows whose source publishes no amount are left out (and counted in the summary). Whol…
- `nihActiveOnly` (boolean): NIH: active projects only. Only return NIH projects that are currently active. Default: off.
- `nihFiscalYears` (array): NIH fiscal years. Optional, e.g. 2025, 2026. Each NIH project appears once (its latest matching year).
- `run_max_charge_usd` (number): Optional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).
- `run_max_items` (integer): Optional. Most results to return from this call (default from PANDA_MAX_ITEMS, 50). Also limits how many results the Actor produces and charges for, unless you set its own max field.
- `run_timeout_secs` (integer): Optional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).
- `sortBy` (string): Sort. Relevance (default) or newest first (by posted / start date). Choices: relevance = Relevance; newest = Newest first.
- `sources` (array): Sources. Grants.gov = open and upcoming funding opportunities you can apply to. NIH RePORTER and NSF = awards already made (who got funded, how much, by which program).

### `federal_contract_finder` (~1315 tokens)

USAspending Scraper: Federal Contract Awards & Recompete Finder

Find US federal prime contract awards on USAspending.gov by keyword, NAICS, PSC, agency, place of performance, set-aside or recipient, or switch to recompete mode to list contracts whose period of performance ends soon. Unlike grants_finder (assistance grants and research awards) and sbir_sttr_topic_radar (open SBIR/STTR topics), this returns procurement contracts with incumbent, UEI and end date. Use when you need incumbents, competitor contract history, market sizing by NAICS/agency, or recompete pipeline leads. Do not use for grants (use grants_finder) or for open solicitations you can bid on today (USAspending holds awards, not SAM.gov notices). Parameters: mode=awards honors sortBy and dateFrom/dateTo (activity window, default last 24 months); mode=recompete ignores sortBy, sorts by soonest end date and uses recompeteMonths as the window. NAICS prefixes cover all child codes. recipientNames accepts company names or UEIs for competitor lookups. Keywords under 3 characters are rejected. Returns per item: agentSummary, awardId, recipientName, recipientUei, amount, awardingAgency, awardingSubAgency, naicsCode, pscCode, description, startDate, endDate, monthsLeft, status, performanceState, url.

Behavior: read-only; runs the Apify Actor pandadad0214/federal-contract-finder (https://apify.com/pandadad0214/federal-contract-finder) on your own Apify account. Price: $0.002 per contract found. Runs that find nothing are not charged per result, and spending is capped per call by run_max_charge_usd (default $0.50). run_max_items (default 50) limits items returned and fills maxResults when you leave it unset, so it also limits what is billed; setting maxResults higher can bill more than is returned. Most calls finish in 5-15 s for a few inputs; large inputs or crawls can take minutes, so raise run_timeout_secs (max 300) or shrink the input after a timeout error. Returns JSON {actor, count, items}; long text output is trimmed to whole items, with all items in structuredCont…

Input parameters:

- `agencies` (array): Awarding agencies. Optional. Department or sub-agency by name or abbreviation, e.g. DOD, VA, GSA, DHS, Department of the Army, Missile Defense Agency, Forest Service.
- `contractTypes` (array): Contract types. Optional. Default: all four prime contract types.
- `dateFrom` (string): Activity from date. Optional. 2024, 2024-06 or 2024-06-30. Awards with a contract action (signed or modified) on or after this date. Default: 24 months ago (36 months in recompete mode). Earliest 200…
- `dateTo` (string): Activity to date. Optional. 2026, 2026-09 or 2026-09-30. Default: today.
- `keywords` (array): Keywords. Words to find in the award description, recipient or codes, e.g. cybersecurity, janitorial, drone. Each keyword at least 3 characters; rows matching any keyword are returned. At least one f…
- `maxAmount` (integer): Maximum award amount (USD). Optional. Whole number, 0 or more USD.
- `maxResults` (integer): Maximum results. You pay per returned contract, so this also caps the cost. Whole number, 1 to 5,000; default 100.
- `minAmount` (integer): Minimum award amount (USD). Optional. Whole number, 0 or more USD.
- `mode` (string): Mode. Contract awards = awards that match your filters, sorted as you choose. Recompete radar = only contracts whose period of performance ends between today and the number of months below (incumbent…
- `naicsCodes` (array): NAICS codes. Optional. 2 to 6 digit NAICS industry codes; a prefix covers all codes under it (5415 = computer systems design). Examples: 541512 IT services, 561720 janitorial, 236220 commercial const…
- `performanceStates` (array): Place of performance (states). Optional. 2-letter US state codes where the work is done, e.g. AZ, TX, DC.
- `pscCodes` (array): PSC codes. Optional. Product and Service Codes (what was bought), e.g. D399 other IT, R425 engineering support, S201 custodial.
- `recipientNames` (array): Recipient (company) names. Optional. Company names or UEIs to look up a competitor's or partner's contracts, e.g. Booz Allen.
- `recompeteMonths` (integer): Recompete window (months). Recompete radar only: keep contracts that end within this many months from today. Whole number, 1 to 36; default 12.
- `run_max_charge_usd` (number): Optional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).
- `run_max_items` (integer): Optional. Most results to return from this call (default from PANDA_MAX_ITEMS, 50). Also limits how many results the Actor produces and charges for, unless you set its own max field.
- `run_timeout_secs` (integer): Optional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).
- `setAsides` (array): Set-aside types. Optional. Only awards made under these small-business set-asides.
- `sortBy` (string): Sort (contract awards mode). Largest awards first, newest start date first, latest end date first, or most recently modified first. Recompete radar always sorts by end date, soonest first. Choices: a…

### `sbir_sttr_topic_radar` (~1055 tokens)

SBIR/STTR Topic Radar: Open Topics, Deadlines & DoD Q&A

Find SBIR and STTR solicitation topics across agencies (DoD branches, NIH, NASA, NSF, DOE, USDA, DHS and more) by keyword, with full topic text, close dates, days left, topic numbers, official links, and DoD Q&A status and technical points of contact. Unlike grants_finder (general Grants.gov opportunities and past NIH/NSF awards) and federal_contract_finder (awarded contracts), this lists small-business R&D topics you can propose to. Use when a small business or research partner needs open SBIR/STTR topics, deadlines or a TPOC to contact. Do not use for general grants (use grants_finder) or for past contract winners (use federal_contract_finder). Parameters: empty keywords lists every topic matching the other filters, which can be large, so keep maxResults low. status=closed returns past topics to show what an agency keeps funding. includeDetails and includeDodQa each fetch extra pages per topic: richer rows, slower runs, same price; turn them off for a fast scan. Searches with no results are free. Returns per item: agentSummary, topicId, topicNumber, title, agency, branch, program, phase, status, openDate, closeDate, daysLeft, description, technicalPointOfContact, dodQaStatus, dodPublishedQuestions, officialSolicitationUrl, url.

Behavior: read-only; runs the Apify Actor pandadad0214/sbir-sttr-topic-radar (https://apify.com/pandadad0214/sbir-sttr-topic-radar) on your own Apify account. Price: $0.003 per topic found. Runs that find nothing are not charged per result, and spending is capped per call by run_max_charge_usd (default $0.50). run_max_items (default 50) limits items returned and fills maxResults when you leave it unset, so it also limits what is billed; setting maxResults higher can bill more than is returned. Most calls finish in 5-15 s for a few inputs; large inputs or crawls can take minutes, so raise run_timeout_secs (max 300) or shrink the input after a timeout error. Returns JSON {actor, count, items}; long text output is trimmed to whole items, wit…

Input parameters:

- `agencies` (array): Agencies. Optional agency or branch codes: DOD (all DoD/DoW), USAF, ARMY, NAVY, DARPA, DHA, DTRA, MDA, SOCOM, SDA, OSD, CBD, HHS, NIH, FDA, CDC, NASA, NSF, DOE, USDA, NIFA, DHS, DOT, ED, EPA, DOC, NI…
- `closeDateFrom` (string): Closes on or after. Optional, e.g. 2026-12 or 2026-12-15.
- `closeDateTo` (string): Closes on or before. Optional, e.g. 2027-03-31.
- `includeDetails` (boolean): Read full topic pages. Adds topic number, solicitation number, branch, due dates, full description and the official solicitation link (one extra page per topic, no extra charge).
- `includeDodQa` (boolean): Add DoD Q&A status and point of contact. For DoD/DoW topics, looks the topic up on the DoD SBIR/STTR Innovation Portal (DSIP) and adds Q&A status, Q&A end date, published-question count and the techn…
- `keywords` (string): Keywords. Words to find in topic titles and text, e.g. autonomy, battery, machine learning, wound care. Leave empty to list every topic with the chosen status.
- `maxResults` (integer): Maximum topics. You pay per topic returned, so this also caps the cost. 1 to 1,000; default 50.
- `program` (string): Program. Topics tagged for both programs are kept either way. Choices: any = SBIR or STTR; SBIR = SBIR only; STTR = STTR only (needs a research-institution partner).
- `run_max_charge_usd` (number): Optional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).
- `run_max_items` (integer): Optional. Most results to return from this call (default from PANDA_MAX_ITEMS, 50). Also limits how many results the Actor produces and charges for, unless you set its own max field.
- `run_timeout_secs` (integer): Optional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).
- `status` (string): Topic status. Open = topics you can still propose to. Closed = past topics, useful to see what an agency keeps asking for. Choices: open = Open (accepting proposals); closed = Closed (past topics, fo…

### `sec_financials_excel` (~745 tokens)

SEC Financials to Excel: EDGAR XBRL Comps & Model Data

Return standardized annual financials for US-listed companies from SEC EDGAR XBRL 10-K data: income statement, balance sheet and cash-flow lines plus EBITDA, free cash flow, net debt, margins and growth, one row per company-year, each number tagged to its source filing. Unlike pdf_table_extractor (any PDF table, best-effort), this reads structured filings and is exact; unlike federal_contract_finder it covers public-company fundamentals, not government spend. Use when you need comps, model inputs or multi-year history for tickers or CIKs. Do not use for private companies, foreign filers without 10-Ks, quarterly data or share prices (not included). Parameters: contactEmail is required by SEC's fair-access rule and is sent only to SEC. Billing is per company-year, so worst case = companies x years; run_max_items does not set years, so cap cost with years and run_max_charge_usd. Unknown tickers are returned free with a status. Returns per item: agentSummary, company, ticker, cik, fiscalYear, periodEnd, form, filed, revenue, grossProfit, operatingIncome, netIncome, epsDiluted, operatingCashFlow, capex, freeCashFlow, ebitda, cash, totalDebt, netDebt, stockholdersEquity, margins, revenueGrowth, epsGrowth, sourceTags. The comps workbook stays in the run's Apify key-value store.

Behavior: read-only; runs the Apify Actor pandadad0214/sec-financials-excel (https://apify.com/pandadad0214/sec-financials-excel) on your own Apify account. Price: $0.002 per company-year of financials. Runs that find nothing are not charged per result, and spending is capped per call by run_max_charge_usd (default $0.50). run_max_items (default 50) limits items returned but does not limit what the Actor bills; use the tool's own limits and run_max_charge_usd. Most calls finish in 5-15 s for a few inputs; large inputs or crawls can take minutes, so raise run_timeout_secs (max 300) or shrink the input after a timeout error. Returns JSON {actor, count, items}; long text output is trimmed to whole it…

Input parameters:

- `companies` (array, required): Companies (tickers or CIKs). US-listed companies that file 10-Ks with the SEC, e.g. AAPL, MSFT, BRK-B or a CIK like 320193. Up to 200 per run.
- `contactEmail` (string, required): Your contact email (required by SEC). SEC requires every automated request to declare a contact in its User-Agent header. It is sent to SEC only and is never stored in the output.
- `run_max_charge_usd` (number): Optional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).
- `run_max_items` (integer): Optional. Most results to return from this call (default from PANDA_MAX_ITEMS, 50). Also limits how many results the Actor produces and charges for, unless you set its own max field.
- `run_timeout_secs` (integer): Optional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).
- `years` (integer): Fiscal years per company. Most recent annual (10-K) periods to return. You pay per company-year row, so this also caps the cost.

### `clinical_trial_leads` (~918 tokens)

Clinical Trial Leads: Sponsors, Sites & Contacts

Find clinical trials on the official ClinicalTrials.gov API by condition, intervention, sponsor, phase, status and site location, with sponsor class, enrollment, dates, central contacts, principal investigators and every study site with its contacts. Unlike pubmed_evidence_table (published articles) and npi_provider_lists (all registered providers), this returns registered studies and the people and sites running them. Use when you need recruiting trials near a location, sponsor or site pipelines, or investigator and site-contact leads for CROs, suppliers or patient referral. Do not use for published results (use pubmed_evidence_table) or for funding (use grants_finder). Parameters: statuses default to recruiting and not-yet-recruiting; add COMPLETED etc. for history. countries/states/city keep trials with at least one matching site and report matchingSiteCount. updatedWithinDays suits weekly schedules. requireContact filters out uncontactable trials before billing. Searches with no results are free. Returns per item: agentSummary, nctId, title, status, phase, conditions, interventions, leadSponsor, sponsorClass, collaborators, enrollment, startDate, primaryCompletionDate, centralContactName, centralContactPhone, centralContactEmail, principalInvestigators, sites, matchingSiteCount, url.

Behavior: read-only; runs the Apify Actor pandadad0214/clinical-trial-leads (https://apify.com/pandadad0214/clinical-trial-leads) on your own Apify account. Price: $0.002 per trial returned. Runs that find nothing are not charged per result, and spending is capped per call by run_max_charge_usd (default $0.50). run_max_items (default 50) limits items returned and fills maxResults when you leave it unset, so it also limits what is billed; setting maxResults higher can bill more than is returned. Most calls finish in 5-15 s for a few inputs; large inputs or crawls can take minutes, so raise run_timeout_secs (max 300) or shrink the input after a timeout error. Returns JSON {actor, co…

Input parameters:

- `city` (string): Site city. e.g. Phoenix.
- `condition` (string): Condition or disease. e.g. obesity, breast cancer, Alzheimer. Uses ClinicalTrials.gov synonyms.
- `countries` (array): Site countries. Keep trials with at least one site here, e.g. United States, Canada.
- `intervention` (string): Drug or intervention. e.g. semaglutide, CAR-T, device name. Optional.
- `keywords` (string): Other keywords. Free-text search across the whole record. Optional.
- `maxResults` (integer): Maximum results. You pay per trial returned, so this also caps the cost. Default 100.
- `phases` (array): Phases. Empty = any phase.
- `requireContact` (boolean): Only trials with a contact. Skip trials without a published central or site contact.
- `run_max_charge_usd` (number): Optional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).
- `run_max_items` (integer): Optional. Most results to return from this call (default from PANDA_MAX_ITEMS, 50). Also limits how many results the Actor produces and charges for, unless you set its own max field.
- `run_timeout_secs` (integer): Optional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).
- `sponsor` (string): Sponsor or collaborator. e.g. Pfizer, Mayo Clinic. Optional.
- `sponsorType` (string): Lead sponsor type. Industry = pharma/biotech/device companies. Choices: any = Any; INDUSTRY = Industry; NIH = NIH; FED = Other federal; OTHER_GOV = Other government; OTHER = Academic / hospital / oth…
- `states` (array): Site states / regions. Full names as on ClinicalTrials.gov, e.g. Arizona, California, Ontario.
- `statuses` (array): Recruitment status. Default: recruiting + not yet recruiting.
- `studyType` (string): Study type. Interventional = treatment trials.
- `updatedWithinDays` (integer): Updated in the last N days. Only trials whose record changed recently (good for weekly schedules).

### `federal_register_monitor` (~837 tokens)

Federal Register Monitor: New Rules & Comment Deadlines

Track new US federal rules, proposed rules, notices and presidential documents from the official FederalRegister.gov API, with agency, publication and effective dates, comment deadline and days left, docket IDs, RIN, abstract and comment links. Unlike grants_finder (assistance opportunities) and federal_contract_finder (awarded contracts), this monitors the Federal Register rulemaking feed. Use when compliance, policy, lobbying or capture teams need new rules or open comment periods by keyword or agency. Do not use for grant RFPs (use grants_finder) or for awarded contract data (use federal_contract_finder). Parameters: keywords and agencies narrow the search; commentsOpenOnly=true keeps only open dockets; documentTypes RULE|PRORULE|NOTICE|PRESDOCU; daysBack or publishedFrom/To set the window; significantOnly filters significant rules; maxResults caps billed documents. Empty runs are free. Returns per item: agentSummary, documentNumber, type, title, agencies, publicationDate, effectiveDate, commentsCloseDate, commentDaysLeft, commentOpen, significant, docketIds, rins, citation, abstract, commentUrl, url, pdfUrl, regulationsGovDocketUrl; plus FEDREG_XLSX/CSV.

Behavior: read-only; runs the Apify Actor pandadad0214/federal-register-monitor (https://apify.com/pandadad0214/federal-register-monitor) on your own Apify account. Price: $0.001 per document returned. Runs that find nothing are not charged per result, and spending is capped per call by run_max_charge_usd (default $0.50). run_max_items (default 50) limits items returned and fills maxResults when you leave it unset, so it also limits what is billed; setting maxResults higher can bill more than is returned. Most calls finish in 5-15 s for a few inputs; large inputs or crawls can take minutes, so raise run_timeout_secs (max 300) or shrink the input after a timeout error. Returns JSON {actor, count, items}; long text output is trimmed to whole items, with all items in structuredContent.

Input parameters:

- `agencies` (array): Agencies. Agency slugs from federalregister.gov/agencies, e.g. environmental-protection-agency, food-and-drug-administration, securities-and-exchange-commission.
- `cfrPart` (integer): CFR part. Optional, with CFR title.
- `cfrTitle` (integer): CFR title. Optional, e.g. 21 (food and drugs), 40 (environment).
- `commentsOpenOnly` (boolean): Only open comment periods. Keep documents you can still comment on, soonest deadline first.
- `daysBack` (integer): Published in the last N days. Use 1 or 7 on a daily or weekly schedule. Default 30.
- `documentTypes` (array): Document types. Empty = all types.
- `keywords` (string): Keywords. Full-text search, e.g. "artificial intelligence", PFAS, overtime. Quotes for exact phrases.
- `maxResults` (integer): Maximum results. You pay per document returned, so this also caps the cost. Default 100.
- `publishedFrom` (string): Published on or after. Optional YYYY-MM-DD; overrides days back.
- `publishedTo` (string): Published on or before. Optional YYYY-MM-DD.
- `run_max_charge_usd` (number): Optional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).
- `run_max_items` (integer): Optional. Most results to return from this call (default from PANDA_MAX_ITEMS, 50). Also limits how many results the Actor produces and charges for, unless you set its own max field.
- `run_timeout_secs` (integer): Optional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).
- `significantOnly` (boolean): Only significant rules. Rules flagged significant under EO 12866.

### `product_recall_monitor` (~773 tokens)

Product Recall Monitor: FDA Food, Drug, Device & CPSC Recalls

Pull one feed of US product recalls from openFDA (food, drug, medical device enforcement) and CPSC SaferProducts.gov (consumer products), with product, reason or hazard, recalling firm, FDA class, status, distribution, lots/UPCs, retailers and remedy. Unlike clinical_trial_leads (registered studies) and federal_register_monitor (rulemaking), this is safety recall enforcement. Use when QA, retail, insurance, marketplace or consumer-safety teams need recent recalls by keyword, firm, class, state or date. Do not use for vehicle VIN recalls (use vin_decoder_recalls) or for clinical-trial safety results. Parameters: sources food|drug|device|consumer (default all); keywords and firmContains filter before billing; classifications Class I|II|III (FDA); daysBack or dateFrom; states for distribution; maxResults caps billed recalls. Empty runs are free. Returns per item: agentSummary, source, recallNumber, date, classification, status, product, reason, firm, firmLocation, firmState, distribution, quantity, codes, retailers, remedy, hazard, url; plus RECALLS_XLSX/CSV.

Behavior: read-only; runs the Apify Actor pandadad0214/product-recall-monitor (https://apify.com/pandadad0214/product-recall-monitor) on your own Apify account. Price: $0.0015 per recall returned. Runs that find nothing are not charged per result, and spending is capped per call by run_max_charge_usd (default $0.50). run_max_items (default 50) limits items returned and fills maxResults when you leave it unset, so it also limits what is billed; setting maxResults higher can bill more than is returned. Most calls finish in 5-15 s for a few inputs; large inputs or crawls can take minutes, so raise run_timeout_secs (max 300) or shrink the input after a timeout error. Returns JSON {actor, count, items}; long text output is trimmed to whole items, with all items in structuredContent.

Input parameters:

- `classifications` (array): FDA class. Class I = most serious. Setting this leaves out CPSC recalls (they have no class).
- `dateFrom` (string): Reported on or after. Optional YYYY-MM-DD; overrides days back.
- `daysBack` (integer): Reported in the last N days. Default 30. Use 7 on a weekly schedule.
- `firmContains` (string): Firm name contains. e.g. a supplier or brand.
- `keywords` (string): Keywords (all must match). Comma-separated, matched in product, reason, firm, lots and retailers, e.g. peanut, listeria, insulin pump.
- `maxResults` (integer): Maximum results. You pay per recall returned, so this also caps the cost. Default 200.
- `run_max_charge_usd` (number): Optional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).
- `run_max_items` (integer): Optional. Most results to return from this call (default from PANDA_MAX_ITEMS, 50). Also limits how many results the Actor produces and charges for, unless you set its own max field.
- `run_timeout_secs` (integer): Optional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).
- `sources` (array): Sources. FDA food, drugs and devices (openFDA, updated weekly) and CPSC consumer products.
- `states` (array): Distributed in states. 2-letter codes; keeps nationwide recalls and FDA recalls whose distribution mentions the state, e.g. AZ.

### `vin_decoder_recalls` (~750 tokens)

VIN Decoder + Recalls: Bulk NHTSA Specs & Safety Recalls

Bulk-decode vehicle identification numbers with the official NHTSA vPIC API and attach NHTSA recall campaigns and complaint counts for each model year in the same run (year, make, model, trim, body, engine, fuel, drivetrain, plant, safety features). Unlike product_recall_monitor (FDA/CPSC product recalls) and company_website_enricher (firmographics), this is VIN-level vehicle data. Use when dealers, fleets, insurers, marketplaces or repair shops need specs plus open safety recalls for many VINs. Do not use for consumer product or drug recalls (use product_recall_monitor) or for title/lien history. Parameters: vins (list; duplicates removed; up to 10,000); includeRecalls and includeComplaints default true; includeInvalid keeps undecodable VINs as free skipped rows; maxResults caps billed decodes. Undecodable VINs are skipped for free. Returns per item: agentSummary, vin, valid, modelYear, make, model, trim, bodyClass, vehicleType, driveType, engine, fuel, manufacturer, plant, safetyFeatures, recallCount, parkItRecall, recalls, complaintCount, nhtsaRecallUrl; plus VINS_XLSX (Vehicles + Recalls sheets)/CSV.

Behavior: read-only; runs the Apify Actor pandadad0214/vin-decoder-recalls (https://apify.com/pandadad0214/vin-decoder-recalls) on your own Apify account. Price: $0.001 per vin decoded. Runs that find nothing are not charged per result, and spending is capped per call by run_max_charge_usd (default $0.50). run_max_items (default 50) limits items returned and fills maxResults when you leave it unset, so it also limits what is billed; setting maxResults higher can bill more than is returned. Most calls finish in 5-15 s for a few inputs; large inputs or crawls can take minutes, so raise run_timeout_secs (max 300) or shrink the input after a timeout error. Returns JSON {actor, count, items}; long text output is trimmed to whole items, with all items in structuredContent.

Input parameters:

- `includeComplaints` (boolean): Add complaint counts. Number of NHTSA owner complaints for the model year (no extra charge).
- `includeInvalid` (boolean): Return VINs that do not decode. On = every VIN gets a row (with the decode note) and is charged. Off = VINs NHTSA cannot decode at all are skipped for free.
- `includeRecalls` (boolean): Add NHTSA recall campaigns. Recall campaigns for each make/model/year, with component, summary, remedy and park-it warnings (no extra charge).
- `maxResults` (integer): Maximum results. You pay per VIN returned, so this also caps the cost. Default 1000.
- `run_max_charge_usd` (number): Optional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).
- `run_max_items` (integer): Optional. Most results to return from this call (default from PANDA_MAX_ITEMS, 50). Also limits how many results the Actor produces and charges for, unless you set its own max field.
- `run_timeout_secs` (integer): Optional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).
- `vins` (array): VINs. Up to 10,000 17-character VINs. Spaces and dashes are removed, duplicates dropped.

### `eu_ted_tenders` (~855 tokens)

EU TED Tenders: Public Procurement Notices

Search official EU TED (Tenders Electronic Daily) public procurement notices through the TED Search API v3, with English title, publication date, buyer country, NUTS, notice and contract type, procedure, estimated or award value when published, tender deadline, CPV codes and TED HTML/PDF links. Unlike federal_contract_finder (US federal awards) and grants_finder (US assistance grants), this covers European public tenders. Use when BD or capture teams, EU suppliers or researchers need tenders by keyword, CPV code or buyer country. Do not use to submit bids, for US opportunities or for national portals outside TED. Parameters: daysBack (default 7) or publishedFrom/To set the window; keywords and cpvCodes (e.g. 72000000 IT services) match the notice; countries takes ISO-3 buyer codes such as DEU or FRA; maxResults caps billed notices. Value is often missing because many notices omit it. Empty input runs a small IT-services demo. Runs with no matches are free. Returns per item: agentSummary, noticeId, title, publicationDate, countries, nuts, noticeType, contractType, procedure, estimatedValue, deadline, CPV codes, noticeUrl, pdfUrl, htmlUrl; plus TED_XLSX/CSV.

Behavior: read-only; runs the Apify Actor pandadad0214/eu-ted-tenders (https://apify.com/pandadad0214/eu-ted-tenders) on your own Apify account. Price: $0.002 per notice returned. Runs that find nothing are not charged per result, and spending is capped per call by run_max_charge_usd (default $0.50). run_max_items (default 50) limits items returned and fills maxResults when you leave it unset, so it also limits what is billed; setting maxResults higher can bill more than is returned. Most calls finish in 5-15 s for a few inputs; large inputs or crawls can take minutes, so raise run_timeout_secs (max 300) or shrink the input after a timeout error. Returns JSON {actor, count, items}; long text output is trimmed to whole items, with all items in structuredContent.

Input parameters:

- `countries` (array): Buyer countries. ISO-3 country codes, e.g. DEU, FRA, ITA, ESP, POL, NLD, BEL, IRL, SWE. Two-letter codes (DE, FR, IT) are converted. Filtered server-side with buyer-country.
- `cpvCodes` (array): CPV codes. Common Procurement Vocabulary codes, e.g. 72000000 (IT services), 45000000 (construction), 33000000 (medical). Several codes are OR'd.
- `daysBack` (integer): Published in the last N days. Default 7. Searches publication-date >= today minus (N-1) days (UTC). Use 1 on a daily schedule. Ignored when Published from / Published to are set.
- `keywords` (array): Keywords. Full-text search. Each keyword becomes FT ~ "..." and they are joined with AND. Quotes are stripped. Example: software, cloud.
- `maxResults` (integer): Maximum results. You pay per notice returned, so this also caps the cost. Default 200; hard max 2000.
- `publishedFrom` (string): Published from. Optional YYYY-MM-DD. Overrides days back for the start of the window.
- `publishedTo` (string): Published to. Optional YYYY-MM-DD.
- `run_max_charge_usd` (number): Optional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).
- `run_max_items` (integer): Optional. Most results to return from this call (default from PANDA_MAX_ITEMS, 50). Also limits how many results the Actor produces and charges for, unless you set its own max field.
- `run_timeout_secs` (integer): Optional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).

### `sam_gov_opportunities` (~1359 tokens)

SAM.gov Contract Opportunities: Open Federal Bids, No API Key

List current US federal contract opportunities from the official SAM.gov public Contract Opportunities data extract (GSA, refreshed daily, no SAM.gov API key): solicitations, combined synopsis/solicitations, presolicitations, sources sought, special notices and award notices, with title, solicitation number, notice type, posted date, response deadline and days left, department/sub-tier/office, NAICS and PSC codes, set-aside, place of performance, contracting officer name, email and phone, and awardee and amount for award notices. Unlike federal_contract_finder (past USAspending awards, incumbents and recompete dates) and grants_finder (assistance grants), this is open SAM.gov notices you can respond to now. Use when small businesses, GovCon BD teams, proposal writers or subcontractors need new bids by NAICS, PSC, set-aside, agency, state or keyword, or award notices to find primes for teaming. Do not use to download attachments or submit bids (open samUrl on SAM.gov), or for state/local or EU tenders (use eu_ted_tenders). Parameters: daysBack (default 7) or postedFrom/postedTo set the posted window (the file is newest first, so short windows are fast); keywords and excludeKeywords match title and description; naicsCodes and pscCodes are prefix matches (e.g. 5415, D3); setAsides takes SAM codes (SBA, 8A, HZC, SDVOSBC, WOSB, EDWOSB, NONE...); noticeTypes, agencies (department/sub-tier/office contains) and states (place of performance or office state) narrow rows; openOnly (default true) drops passed deadlines but keeps notices with no deadline; minDaysToDeadline keeps biddable notices only; requireContactEmail; descriptionChars (default 600); maxResults caps billed notices. Runs with no matches are free. Returns per item: agentSummary, noticeId, title, solicitationNumber, noticeType, postedDate, responseDeadline, daysToDeadline, department, subTier, office, naicsCode, pscCode, setAsideCode, setAside, popCity, popState, awardDate, awardAmount, awardee, contactName, co…

Input parameters:

- `activeOnly` (boolean): Active notices only. Default on (SAM.gov Active = Yes).
- `agencies` (array): Agency contains. Match department, sub-tier or office (case-insensitive), e.g. veterans affairs, army, GSA, NASA.
- `daysBack` (integer): Posted in the last N days. Default 7. Matches the SAM.gov posted date. Use 1 or 2 on a daily schedule. The source file is newest first, so short windows are fast.
- `descriptionChars` (integer): Description length. Characters of the notice description to include. Default 600; 0 = none.
- `excludeKeywords` (array): Exclude keywords. Drop notices containing any of these words, e.g. brand name only.
- `keywords` (array): Keywords (any). Keep notices whose title or description contains any of these words or phrases (case-insensitive), e.g. janitorial, cybersecurity, HVAC.
- `maxResults` (integer): Maximum results. You pay per notice returned, so this also caps the cost. Default 500; hard max 10000.
- `minDaysToDeadline` (integer): At least N days to deadline. Optional. Keep notices with at least this many days left to respond (drops notices with no deadline).
- `naicsCodes` (array): NAICS codes (prefix). Starts-with match, e.g. 5415 (IT services), 541330 (engineering), 236220 (commercial building), 561720 (janitorial).
- `noticeTypes` (array): Notice types. Empty = all. Award Notice rows carry the awardee and amount (teaming and subcontracting leads).
- `openOnly` (boolean): Open only. Default on. Drops notices whose response deadline has passed. Notices with no deadline (award notices, many special notices) are kept.
- `postedFrom` (string): Posted on or after. Optional YYYY-MM-DD; overrides days back.
- `postedTo` (string): Posted on or before. Optional YYYY-MM-DD.
- `pscCodes` (array): PSC codes (prefix). Product/service code starts-with, e.g. D3 (IT), R4 (professional services), Z2 (building repair), S2 (housekeeping).
- `requireContactEmail` (boolean): Only with a contracting contact email. Keep notices that list a primary point-of-contact email.
- `run_max_charge_usd` (number): Optional. Hard spending cap for this call in USD (default from PANDA_MAX_CHARGE_USD, 0.50).
- `run_max_items` (integer): Optional. Most results to return from this call (default from PANDA_MAX_ITEMS, 50). Also limits how many results the Actor produces and charges for, unless you set its own max field.
- `run_timeout_secs` (integer): Optional. Seconds to wait for results (default from PANDA_TIMEOUT_SECS, 120; max 300).
- `setAsides` (array): Set-asides. Empty = any. NONE keeps notices with no set-aside (full and open).
- `states` (array): States. Two-letter codes matched on the place of performance or the contracting office state, e.g. AZ, TX, VA.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/pandadad0214-panda-public-funding-tools/panda-public-funding-tools#diagnostics

## Score history

- 2026-11-21: 68
- 2026-11-20: 83
- 2026-11-19: 82
- 2026-11-18: 82
- 2026-11-17: 66
- 2026-11-16: 81
- 2026-11-15: 80
- 2026-11-14: 65
- 2026-11-13: 79
- 2026-11-12: 79
- 2026-11-11: 64
- 2026-11-10: 63
- 2026-11-09: 63

## Common questions

### What is the Panda Public Funding Tools MCP server?

Panda Public Funding Tools is an MCP server listed in the public MCP registry as io.github.pandadad0214/panda-public-funding-tools. Public money & safety: grants, contracts, SAM.gov bids, SBIR, SEC, FedReg, recalls, EU tenders (10). This page covers its PyPI package (panda-public-funding-tools).

### Is the Panda Public Funding Tools MCP server safe to use?

Panda Public Funding Tools scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. 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 Panda Public Funding Tools MCP server expose?

Panda Public Funding Tools exposes 10 tools: grants_finder, federal_contract_finder, sbir_sttr_topic_radar, sec_financials_excel, clinical_trial_leads, and 5 more. Their descriptions and schemas cost roughly 9,815 tokens of context every time the server is loaded.

### Is the Panda Public Funding Tools MCP server still maintained?

Panda Public Funding Tools is still listed as active in the MCP registry. We last reached this channel on 21 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 Panda Public Funding Tools MCP server under?

Panda Public Funding Tools 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 Panda Public Funding Tools MCP server?

VerifyMCP ran 15 checks on Panda Public Funding Tools, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about Panda Public Funding Tools: Malware scan. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/panda-public-funding-tools/
- Socket report: https://socket.dev/pypi/package/panda-public-funding-tools
- Repository: https://github.com/pandadad0214/panda-public-funding-tools
- Changelog RSS feed: https://verifymcp.io/servers/pandadad0214-panda-public-funding-tools/panda-public-funding-tools.xml
- Changelog JSON feed: https://verifymcp.io/servers/pandadad0214-panda-public-funding-tools/panda-public-funding-tools/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/pandadad0214-panda-public-funding-tools/panda-public-funding-tools.json
- HTML version of this page: https://verifymcp.io/servers/pandadad0214-panda-public-funding-tools/panda-public-funding-tools
