Panda Research Tools
# Panda Research Tools
**Scholarly integrity and papers: citation checks, literature and PubMed search, academic experts, PDF tables.**
Focused MCP server (6 tools) from the [Panda Federation](https://github.com/pandadad0214/panda-federation-tools) public-data toolkit. Prefer this over the 23-tool mega-server for better Tool Definition Quality Score (TDQS) / Glama coherence.
[](https://github.com/pandadad0214/panda-federation-tools)
[](https://apify.com/pandadad0214)
[](LICENSE)
## Install / Use
Needs a free [Apify API token](https://console.apify.com/settings/integrations) and [uv](https://docs.astral.sh/uv/).
```bash
uvx --from panda-federation-tools panda-research-tools
```
Same entry point from this repo:
```bash
uvx --from git+https://github.com/pandadad0214/panda-research-tools panda-research-tools
```
Cursor / Claude / VS Code: command `uvx`, args `["--from", "panda-federation-tools", "panda-research-tools"]`, env `APIFY_TOKEN`.
## Tools (6)
- `reference_checker`
- `citation_formatter`
- `literature_search`
- `pubmed_evidence_table`
- `researcher_expert_finder`
- `pdf_table_extractor`
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](https://github.com/pandadad0214/panda-federation-tools#domain-tool-lists).
## Sibling domain servers
- [`panda-public-funding-tools`](https://github.com/pandadad0214/panda-public-funding-tools) — US federal money and filings: grants, contracts, SBIR/STTR topics, SEC financials, clinical trials.
- [`panda-leads-tools`](https://github.com/pandadad0214/panda-leads-tools) — Public leads and enrichment: NPI providers, podcasts, local businesses, hiring signals, website enrichment, team pages, topic trends, trucking carriers.
- [`panda-web-security-tools`](https://github.com/pandadad0214/panda-web-security-tools) — Site, email and agent safety: SPF/DKIM/DMARC audits, AI/SEO readiness, website change monitoring, hidden AI instructions scanner.
Index / compatibility mega-server: [panda-federation-tools](https://github.com/pandadad0214/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](https://github.com/pandadad0214/panda-federation-tools) / project docs.
Built by Panda Federation. MIT licensed.
TDQS
Scored across 6 tools
Each tool occupies a distinct slot in the research workflow: discover papers (literature_search), screen biomedical literature (pubmed_evidence_table), format citations (citation_formatter), audit references (reference_checker), find people (researcher_expert_finder), and pull tables from PDFs (pdf_table_extractor). Descriptions explicitly name the nearest neighbour and give a 'Do not use X, use Y' rule for the only genuinely close pairs (check vs. format, OpenAlex vs. PubMed). The residual overlap of literature_search/pubmed returning ready-made citations is a side output, not a competing use case.
All six names follow the same snake_case <subject>_<function> compound pattern (reference_checker, citation_formatter, literature_search, researcher_expert_finder, pdf_table_extractor, pubmed_evidence_table). No mixing of camelCase, verb-first, or vague one-word names; each name states the resource and the operation.
Six tools is well within the sweet spot and each maps to a clearly separate stage of a literature/research pipeline, so nothing feels redundant or padded. No obvious missing capability is being papered over by splitting or merging tools.
The surface covers the discovery → screening → verification → formatting loop plus two adjacent needs (expert finding, PDF table extraction), which is strong lifecycle coverage for a research toolkit. Minor gaps remain: no full-text/abstract-level reading or data-extraction tool for a specific paper, and no library/deduplication management across result sets, but agents can work around these via literature_search output and pdf_table_extractor.