Panda Research Tools
Give Claude, Cursor or any MCP client 7 research-integrity tools: catch fake or retracted citations, search OpenAlex and PubMed, find experts, pull PDF tables and find Wayback snapshots. Each tool runs one public-data Apify Actor on your own Apify account and is priced per result. Part of the Panda Federation toolkit (36 tools in four focused servers).
How to use this
uvx panda-research-tools
- Get a free Apify token at console.apify.com/settings/integrations (the free plan includes $5 of monthly credit) and install uv.
- Add the server to your MCP client: command
uvx, args["panda-research-tools"], envAPIFY_TOKEN(Cursor JSON below). - Ask in plain words, e.g. "Check these 12 references for fake or retracted papers and format the good ones in APA." Start with one or two inputs and read the
summary/agentSummaryline before widening.
{"mcpServers": {"panda-research-tools": {"command": "uvx", "args": ["panda-research-tools"], "env": {"APIFY_TOKEN": "apify_api_YOUR_TOKEN"}}}}
For AI agents
| Field | Value |
|---|---|
| Purpose | Focused MCP server with 7 research-integrity tools: catch fake or retracted citations, search OpenAlex and PubMed, find experts, pull PDF tables and find Wayback snapshots. |
| Use when | A task needs verified scholarly sources: citation checks, literature or PubMed search, expert finding, PDF tables or archived page snapshots. |
| Do not use when | The task is about federal money (use panda-public-funding-tools), sales leads (panda-leads-tools) or site/email safety (panda-web-security-tools). |
| Install | uvx panda-research-tools (stdio, Python 3.11+) |
| Auth | APIFY_TOKEN env var; runs bill to that Apify account. |
| Tools | 7, listed under Tools |
| Outputs | JSON rows plus a one-line summary / agentSummary; Excel/CSV files on the Apify run. |
| Side effects and cost | Starts Apify runs; pay per result; empty runs are not charged per result; run_max_charge_usd caps each call. Read-only toward third-party sites. |
Other ways to install
From the umbrella package (same tools):
uvx --from panda-federation-tools panda-research-tools
From this repo instead of PyPI:
uvx --from git+https://github.com/pandadad0214/panda-research-tools panda-research-tools
Cursor / Claude / VS Code: command uvx, args ["panda-research-tools"], env APIFY_TOKEN.
Docker (stdio, non-root). APIFY_TOKEN is required:
docker build -t panda-research-tools .
docker run -i --rm -e APIFY_TOKEN panda-research-tools
Official MCP Registry name for this stdio package: io.github.pandadad0214/panda-research-tools (server.json). That name is separate from the hosted companion io.github.pandadad0214/panda-research-mcp. Registry clients install the PyPI package with uvx panda-research-tools. The git command above stays the install path from this repo.
Tools (7)
reference_checkercitation_formatterliterature_searchpubmed_evidence_tableresearcher_expert_finderpdf_table_extractorwayback_snapshot_finder
Each tool runs one Apify Actor on your account. Empty runs are not charged per result; every call is capped by run_max_charge_usd. Full schemas and prices: umbrella README.
Sibling domain servers
panda-public-funding-tools— US federal money, filings and safety monitors: grants, contracts, SBIR/STTR topics, SEC financials, clinical trials, Federal Register, recalls, VIN decode.panda-leads-tools— Public leads and enrichment: NPI providers, podcasts, local businesses, hiring signals, website enrichment, team pages, topic trends, trucking carriers, IRS nonprofits, building permits, new Florida, Texas and New York businesses, H-1B visa sponsors, EU tenders.panda-web-security-tools— Site, email and agent safety: SPF/DKIM/DMARC audits, AI/SEO readiness, website change monitoring, hidden AI instructions scanner, bulk domain WHOIS/expiry, broken link checker.
Index / compatibility mega-server: panda-federation-tools (use only when you truly need every tool).
TDQS standard
New tools join this domain only while the count stays in the 3–15 band. Descriptions follow the checklist in the umbrella repo. See tdqs-standard / project docs.
Built by Panda Federation. MIT licensed.
Metadata
Release files for panda-research-tools 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| panda_research_tools-0.1.0.tar.gz | 59.6 kB | With provenance | Details for panda_research_tools-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| panda_research_tools-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for panda_research_tools-0.1.0-py3-none-any.whl |
Total release size: 65.0 kB
Release files / panda_research_tools-0.1.0.tar.gz
| Download URL | panda_research_tools-0.1.0.tar.gz |
|---|---|
| Size | 59.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
aa0f21ab94178f150e089228da5e5cfbfce3896ca8bca2df6cd196973fe20ff7
|
|
BLAKE2b-256 checksum How to use checksums |
ea1d6c16eee2eafc6ffed9632b96dbd119d02c691caf0161a20110aff64d6729
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 9, 2026.
Transparency logRelease files / panda_research_tools-0.1.0-py3-none-any.whl
| Download URL | panda_research_tools-0.1.0-py3-none-any.whl |
|---|---|
| Size | 5.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c00d8b525e34c7319ab374d04d6eeda00eb42cbded20a9780e6f60bf2c1fac17
|
|
BLAKE2b-256 checksum How to use checksums |
fd2a58cd2cdb0337387e0d70a0fb55a4d84c7fe4a0c3a417f8404ce95a9551b7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 9, 2026.
Transparency logSecurity for panda-research-tools 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for panda_research_tools-0.1.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 9, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.