Literature Evidence MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_PORT | No | Port used when running the server with `MCP_TRANSPORT=streamable-http`, for example `8000`. The MCP endpoint is then `http://127.0.0.1:8000/mcp`. | |
| MCP_TRANSPORT | No | Transport mode for the MCP server. Set to `streamable-http` to run local HTTP instead of the default stdio transport. | |
| OPENALEX_API_KEY | No | OpenAlex API key. OpenAlex basic queries can be keyless but have a restrictive daily budget; obtain a key and set `OPENALEX_API_KEY` for regular use. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_literatureC | Search OpenAlex, Europe PMC, Crossref; deduplicate DOI and report each provider error. |
| search_literature_extendedC | Search four sources, including optional Semantic Scholar; never claim exhaustive recall. |
| expand_citation_chainC | Bounded OpenAlex citation links, forward/backward; edges remain unverified metadata. |
| get_paperA | Get Crossref DOI metadata and source links; does NOT validate scientific conclusions. |
| verify_citationB | Verify bibliographic DOI/title match in Crossref (not validity of the publication). |
| check_retractionB | Inspect Crossref update-to and Retraction Watch-linked updates; absence is inconclusive. |
| read_fulltextA | Read OA full-text XML by PMCID from Europe PMC, with source hash and truncation flag. |
| verify_source_quoteB | Retrieve Europe PMC full text and locate quote in source paragraphs; NOT a scientific verdict. |
| verify_claimB | Check literal quote presence. This cannot scientifically verify a claim. |
| assess_methodologyC | Transparent phrase screening only; NOT a RoB-2, GRADE, or statistical audit. |
| audit_methodologyB | Audit traceability of outcome-specific, user-annotated methods evidence. Quotes are checked against supplied raw text. Labels are never scientifically validated. Human RoB2/ROBINS-I assessment remains necessary. |
| audit_pmc_methodologyC | Fetch Europe PMC XML and validate user annotations against direct JATS paragraphs. No scientific conclusion, risk-of-bias judgement or absence claim is inferred. |
| check_statistical_reportingA | Find mechanically inconsistent p values/CIs/sample-size entries, not test results. |
| export_bibliographyB | Export supplied metadata as BibTeX/RIS/CSL-JSON; NOT scientific verification. |
| compare_studiesC | Compare supplied bibliographic metadata; no inferred theoretical disagreements. |
| find_data_and_codeB | Find Crossref links to supplements/data/software, if registered; do not fetch them. |
| build_evidence_graphC | Validate user-supplied evidence graph with traceable evidence identifiers. |
| log_review_searchC | Search + log reproducible search records; NOT an exhaustive systematic review. |
| export_evidenceC | Append a JSON evidence record to local hash-chained JSONL ledger. |
| verify_evidence_ledgerA | Check local JSONL ledger integrity; cannot detect replacement of the entire ledger. |
| rust_locate_quoteC | Opt-in Rust PyO3 literal quote match, no interpretation of scientific meaning. |
| go_parallel_provider_statusC | Opt-in concurrent Go status probe for three fixed literature APIs. |
| cpp_fixed_effect_metaC | Opt-in C++ fixed-effect numerical pooling; heterogeneity/bias not assessed. |
| record_risk_of_biasC | Record two human RoB2/ROBINS-I V2 Nov-2025 appraisals, flag disagreements. |
| record_gradeC | Record human GRADE reasoning without inferring a validated certainty score. |
| prisma_dual_screenD | Two independent reviewer screening decisions and one-stage PRISMA flow counts. |
| pdf_page_provenanceD | User-supplied PDF: page hash, quote offsets, table and image bounding boxes. |
| propagation_alertsC | Source-linked correction/retraction alerts without treating citations as retractions. |
| cpp_random_effectsC | DerSimonian-Laird, Q, I², tau², approximate interval and leave-one-out. |
| go_literature_recordsC | Opt-in Go metadata retrieval, local cache and five-second request gate. |
| prisma_review_flowD | Auditable PRISMA identification/screening and explicit missing full-text stages. |
| crossref_update_alertsC | Fetch Crossref publication notices and flag citation descendants for review. |
| bm25_rank_evidenceC | Opt-in BM25 of caller-supplied abstracts; never certifies scientific support. |
| nli_assess_evidenceC | Offline pinned NLI support/refute/insufficient MODEL estimate; never verified truth. |
| nli_assess_challenger_evidenceC | Explicitly selected, locally pinned experimental NLI; never scientific proof. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 35 tools
The set has many closely related tools whose boundaries require careful reading: search_literature vs search_literature_extended vs log_review_search, verify_citation vs verify_claim vs verify_source_quote vs rust_locate_quote, and assess_methodology vs audit_methodology vs audit_pmc_methodology. Descriptions do help distinguish them, but the sheer number of near-overlapping verification and methodology tools creates real misselection risk.
Most names follow a snake_case verb_noun or noun_action pattern, making the set broadly readable. There are minor deviations such as language-prefixed tools (rust_, go_, cpp_, nli_, bm25_) and noun-first names like prisma_dual_screen and propagation_alerts, but conventions are not chaotic.
At 35 tools, the surface is heavy for a single evidence-workflow server, and several tools appear to be optional language-specific or experimental variants rather than essential operations. The count exceeds the reasonable 3-15 range and introduces redundancy that makes the set harder to navigate.
The server covers a broad systematic-review lifecycle: literature search, metadata retrieval, full-text access, screening, risk-of-bias/GRADE recording, citation checking, statistical checks, bibliography export, and ledger verification. Some stages are explicitly incomplete or non-inferential, such as missing full-text PRISMA stages and deliberately non-validated methodology screening, but most core workflows have corresponding tools.