Give Claude, Cursor or any MCP client 40 public-data tools for research, US federal funding, B2B leads and web security, split into four focused servers. Each tool runs an Apify Actor on your own Apify account over official open data, priced per result (most $0.001–$0.004), and the free plan's $5 monthly credit covers trying them. ⬇ Download the latest Release · Changelog Landing page: pandadad0214.github.io/panda-federation-tools Part of Panda Federation This project is a module of the Panda Federation — public-data tools, MCP servers, and local-first apps in one catalog. See the rest of the work, including books when they publish and the matching free or paid editions of this tool, at the official site. Follow on X: @PandaFedHQ How to use this uvx --from panda-federation-tools panda-research-tools Get a free Apify token at console.apify.com/settings/integrations and install uv (curl -LsSf https://astral.sh/uv/install.sh | sh). Pick one domain server from the table below (research, public funding, leads or web security) and add it to your MCP client with APIFY_TOKEN in its env (copy-paste configs below). Ask in plain words, e.g. "Check these 12 references for fake or retracted papers." Start with one or two inputs, read the summary / agentSummary line, then widen. No install? Use the hosted research subset (see Hosted options). Landing page and chooser: pandadad0214.github.io/panda-federation-tools. For AI agents Install for your client (focused servers) You need: a free Apify API token (the free plan includes $5/month) and uv (one command: curl -LsSf https://astral.sh/uv/install.sh | sh, or on Windows powershell -c "irm https://astral.sh/uv/install.ps1 | iex"). Replace apify_api_YOUR_TOKEN below with your token, and never commit a file that contains it. Or set PFT_DOMAIN to research | public-funding | leads | web-security while running uvx panda-federation-tools. Each domain also has its own thin GitHub repo (same console script names via uvx once published on PyPI). Related offline guidance (not an Apify wrapper) Quiet File Team MCP is a separate focused server with six free offline tools: explain_method, generate_team_config, generate_early_exit, validate_layout_manifest, draft_workflow and draft_owner_batch. It does not read arbitrary files, call network APIs, or wrap Actors. Related document tool (not an MCP wrapper) Manual Remake rewrites a confusing PDF or photo manual into a clear printable English PDF. Free sample (no upload, no key), Text-only, and Standard share one Actor page — see the Store README for switch steps. Quiet File Team MCP install: uvx --from git+https://github.com/pandadad0214/quiet-file-team-mcp.git@v0.1.0 quiet-file-team-mcp. The file-first Bash core is free at quiet-file-team; a paid setup kit is live on Agensi ($29 one-time) and Apify ($29 per generated kit). Cursor plugin (cursor.directory) This repo ships a Cursor plugin manifest so cursor.directory and Cursor can auto-detect the four focused MCP servers: .cursor-plugin/plugin.json — name, logo, APIFY_TOKEN variable mcp.json — uvx --from panda-federation-tools for research, public funding, leads, and web security Set APIFY_TOKEN when Cursor prompts (Plugins → Configure). Prefer one focused server over enabling all four at once. Cursor example (research) { "mcpServers": { "panda-research-tools": { "command": "uvx", "args": ["--from", "panda-federation-tools", "panda-research-tools"], "env": { "APIFY_TOKEN": "apify_api_YOUR_TOKEN" } } } } Claude Desktop / Claude Code / VS Code Same pattern: command uvx, args ["--from", "panda-federation-tools", "panda-research-tools"] (or another domain script), env APIFY_TOKEN. Claude Desktop .mcpb from the latest Release still installs the umbrella (all tools); prefer a domain script in JSON configs. Claude Code claude mcp add panda-research-tools --env APIFY_TOKEN=apify_api_YOUR_TOKEN -- \ uvx --from panda-federation-tools panda-research-tools Compatibility mega-server (not recommended as the default) uvx panda-federation-tools Lists all 40 tools. Kept for older configs. Prefer a focused domain server above. Other ways to install Pinned to a git tag: uvx --from git+https://github.com/pandadad0214/panda-federation-tools@v1.8.1 panda-research-tools From the Release download: uvx --from https://github.com/pandadad0214/panda-federation-tools/releases/download/v1.8.1/panda_federation_tools-1.8.1-py3-none-any.whl panda-research-tools Helper script: download install.sh (macOS/Linux) or install.ps1 (Windows) from the latest Release. pip: pip install panda-federation-tools then panda-research-tools (or another domain script). Docker: docker build -t panda-federation-tools https://github.com/pandadad0214/panda-federation-tools.git#v1.8.1 then docker run -i --rm -e APIFY_TOKEN -e PFT_DOMAIN=research panda-federation-tools. No install? Hosted research subset (4 tools) at https://pandadad0214--panda-research-mcp.apify.actor/mcp with header Authorization: Bearer . See Hosted options. What's included Official, free data sources only: Crossref, OpenAlex, PubMed, Unpaywall, Grants.gov, NIH, NSF, USAspending, NPI Registry, FMCSA, public DNS, Apple Podcasts, OpenStreetMap, Wikimedia, IRS, Federal Register, FDA, CPSC, NHTSA, city building-permit portals, Florida Sunbiz, Texas Comptroller, New York DOS, Colorado SOS, French SIRENE/RNE, SAM.gov, DOL OFLC LCA data, EU TED, public RSS/Atom feeds, RDAP, the Internet Archive, public job-board feeds and companies' own websites. No logins, no paywalls, no LinkedIn scraping. Pay per result, capped: a few tenths of a cent per result; runs that find nothing are not charged per result; every MCP call has a hard USD spending cap. Agent-friendly output: JSON with a one-line summary or agentSummary per row and OK / CHECK / FIX status where it applies. Your token stays yours: the server runs on your machine and sends your APIFY_TOKEN only to api.apify.com, in a header. It is never logged or returned. Domain tool lists Research (panda-research-tools) — 8 tools Public funding (panda-public-funding-tools) — 10 tools Leads (panda-leads-tools) — 15 tools Web security (panda-web-security-tools) — 7 tools Every tool also accepts three optional run controls: run_max_items (results to return, default 50), run_max_charge_usd (spending cap for the call, default $0.50) and run_timeout_secs (default 120, max 300). While a run is in progress the server sends MCP progress notifications every few seconds, so clients that support them do not time out. Most tools answer in 5–15 seconds for a few inputs; local_business_leads and big crawls can take a minute or more, so give them run_timeout_secs: 300. Also on Apify: the hosted Academic Research MCP Server ($0.01–$0.02 per call). Hidden AI Instructions Watch is our public, evidence-only log of what the free scanner finds. Example prompts "Check these 12 references for fake or retracted papers and tell me which to fix." "Find 20 recent peer-reviewed papers on GLP-1 and heart failure with free PDFs, then format them in APA." "Which of these 30 SaaS companies are hiring sales leaders right now? Then find their VP-level contacts." "Audit the email security of acme.com and its three competitors, and list the fixes." "List dentists in Phoenix, AZ with a website and phone number." Typical workflows Writing a paper: literature_search → citation_formatter → reference_checker before you submit. Systematic review: pubmed_evidence_table (evidence table + PRISMA counts) → reference_checker. Funding: grants_finder → literature_search on the topic. Federal contracting: federal_contract_finder (recompete radar + top incumbents) → sam_gov_opportunities for the open solicitations (NAICS + set-aside). Account prioritization: company_hiring_signals → company_website_enricher → email_domain_security_checker. Outbound to decision makers: company_hiring_signals → company_team_finder (names, titles, email pattern). Local prospecting: local_business_leads → ai_search_seo_audit on their websites. Trucking and logistics sales: trucking_company_leads → company_website_enricher. New-business outreach: florida_new_business_leads, texas_new_business_leads new_york_new_business_leads or colorado_new_business_leads (self-agent owners) → company_website_enricher. Visa sponsors: h1b_lca_sponsor_leads → company_team_finder for the hiring contacts. EU tenders: eu_ted_tenders (CPV + country) for European buyers; sam_gov_opportunities is the US counterpart. French B2B lists: france_company_leads (NAF + department + size) → company_website_enricher. Daily digest: rss_feed_monitor (only new items, keywords) on competitor blogs and regulator feeds → website_change_monitor for pages without a feed. Site health: broken_link_checker → wayback_snapshot_finder to recover dead pages. Contractor and supplier sales: building_permit_leads (sortBy value) → local_business_leads. Domain portfolio: bulk_domain_whois_expiry (only expiringSoon) → email_domain_security_checker. Dead links and dated evidence: wayback_snapshot_finder → reference_checker. Market research: topic_trends_tracker → literature_search or podcast_leads_finder on rising topics. You pay Apify per result, at the prices above, from your own Apify account. Apify Bronze, Silver and Gold plans get 10–30% off. Empty runs cost nothing per result. Apify adds a tiny platform start fee (about $0.00005 per run). run_max_items (default 50) also sets the Actor's own result limit on 36 of the 40 tools, so you only pay for the results you asked for. On grants_finder, pdf_table_extractor, company_team_finder and sec_financials_excel (whose limits count sources, pages, companies or years), set those fields directly; the charge cap still applies. Every MCP call is capped by run_max_charge_usd (default $0.50, set your own default with PANDA_MAX_CHARGE_USD). Apify stops the run when the cap is reached. The MCP server itself is free and open source (MIT). Configuration Security and permissions Runs locally over stdio. It opens no ports and calls only https://api.apify.com. Token handling: read from the environment, sent only as an Authorization: Bearer header (never in a URL), redacted from every error message, and never logged or returned to the model. Least privilege: the token needs permission to run Actors. Apify supports scoped API tokens; a token limited to running these Actors is enough. Read-only tools: every tool only reads public data; none writes to your systems. Tools are marked readOnlyHint: true. Validated inputs: every call is checked against the Actor's JSON Schema (types, ranges, enums, no unknown fields) before it runs. Secret Actor inputs (such as optional third-party API keys) are deliberately not exposed to the model. Bounded cost and time: per-call spending cap, item cap and timeout. The server retries once only when Apify never started a run (rate limit or failed connection), so a retry can never charge you twice. Context-safe output: large results are trimmed to whole items (still valid JSON) for the model, with every item kept in structuredContent. Supply chain: pinned dependencies with a committed uv.lock, pip-audit and CodeQL in CI, Dependabot updates, and GitHub Actions pinned to commit SHAs. Found a vulnerability? See SECURITY.md. Hosted options (no install) Academic Research MCP Server (Streamable HTTP): https://pandadad0214--panda-research-mcp.apify.actor/mcp with header Authorization: Bearer . Four research tools (check_references, format_citations, search_literature, pubmed_evidence_table). This is the server listed in the official MCP Registry as io.github.pandadad0214/panda-research-mcp (server.json) — a hosted research subset, not the full index. The full stdio umbrella is io.github.pandadad0214/panda-federation-tools (server-federation-tools.json). Apify's MCP server: https://mcp.apify.com can call any of these Actors as pandadad0214/. Plain HTTP API: curl -X POST "https://api.apify.com/v2/acts/pandadad0214~reference-checker/run-sync-get-dataset-items" \ -H "Authorization: Bearer $APIFY_TOKEN" -H "Content-Type: application/json" \ -d '{"dois": ["10.1038/nature14539"]}' Agent skills (Agensi) Ready-made skills that wrap these tools for AI agents are listed on the Panda Federation Agensi profile. Each skill runs the Apify tools above, so the usual pay-per-result prices apply on top of the skill price. Medical Writing Pack: evidence tables, ref checks and KOLs ($12) RFP Compliance Matrix + Incumbent Intel (free) GEO & SEO Site Audit ($4.99) Email Deliverability Audit: SPF/DKIM/DMARC in bulk (free) Citation Check: fake, miscited and retracted references (free) Hire a human (Fiverr) Prefer a person to run the tools and hand you finished files? Panda Federation also sells these as Fiverr gigs (seller pandafederation). Professional use only, not for coursework. For developers For AI agents and LLMs llms.txt: short index of every tool and when to use it (llms.txt convention). llms-full.txt: each tool's inputs, outputs and prices in one file. llms-install.md: step-by-step setup for AI coding agents such as Cline. Every result has a one-line summary field (summary on the citation, literature, PubMed, PDF, NPI and expert tools; agentSummary on the others), and every run saves a SUMMARY record with a takeaway and the suggested next tool. Start small (one or two inputs), read the summary line, then widen. Build, test and contribute git clone https://github.com/pandadad0214/panda-federation-tools && cd panda-federation-tools uv sync # installs pinned dependencies from uv.lock uv run pytest # offline tests, no token or network needed uv run ruff check . && uv run mypy python scripts/build_catalog.py # refresh tool schemas and prices from the Apify Store Layout: src/panda_federation_tools/ (server, Apify client, domains, bundled catalog.json), tests/, scripts/build_catalog.py, Dockerfile. See CONTRIBUTING.md and CHANGELOG.md. New tools join the matching domain only; if a domain would exceed ~15 tools, split that domain before shipping. Issues and requests Open an issue here or on any tool's Apify Issues tab. We answer within a day. Built by Panda Federation with AI assistance. MIT licensed.
AI NEWS JOURNAL
Hacker News Show HNAI NEWS / JOURNAL
Show HN: Open-source MCP server for pay-per-result research/public-data tools
Article URL: https://github.com/pandadad0214/panda-federation-tools Comments URL: https://news.ycombinator.com/item?id=50555500 Points: 1 # Comments: 0