Literature Evidence MCP
Literature Evidence MCP is a scientific literature search, provenance, and evidence-audit toolset—not a peer reviewer, meta-analysis engine, or truth oracle.
Search bibliographic metadata across OpenAlex, Europe PMC, Crossref, and optionally Semantic Scholar; deduplicate DOIs and preserve provider errors.
Expand bounded citation chains and inspect Crossref/Retraction Watch notices and citation descendants for review.
Retrieve paper metadata, publisher links, registered data/code links, and verify DOI/title citation matches.
Read Europe PMC full text and verify literal source quotes with paragraph IDs, offsets, hashes, and truncation flags.
Check literal quote presence in supplied text, screen methodology phrases, and audit human-supplied methodology annotations against raw or PMC text.
Screen supplied statistical reporting for mechanical inconsistencies without recomputing analyses.
Compare study metadata, build evidence graphs, log reproducible searches, and append/verify a local hash-chained evidence ledger.
Export bibliographic records to BibTeX/RIS/CSL-JSON and export evidence records.
Record two-reviewer risk-of-bias and GRADE reasoning, dual screening, PRISMA flow/checklist accounting, and PDF page/table/image provenance.
Use optional BM25 evidence ranking and experimental NLI support/refute/insufficient estimates; neither certifies scientific truth.
Use optional native accelerators: Rust literal quote matching, Go provider status/metadata retrieval, and C++ fixed-effect/random-effects numerical pooling.
All tools distinguish bibliographic facts, text matches, and workflow/numeric helpers from validated scientific conclusions; absence of results or retraction notices is inconclusive.
Provides optional literature search through Semantic Scholar as an additional metadata source, alongside OpenAlex, Europe PMC, and Crossref, with per-provider error reporting and no guarantee of exhaustive recall.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Literature Evidence MCP Search recent CRISPR cancer papers and check if the top citation is retracted."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Literature Evidence MCP
An open-source scientific literature and evidence provenance MCP server.
Important: v0.5.1 is a bibliographic/traceability and evidence-audit toolset, NOT an automated peer reviewer, meta-analysis engine, certified PRISMA-compliant review engine, validated quality score, or scientific truth oracle. It never labels a paper scientifically proven solely from an abstract or citation. The v0.5 PRISMA and PDF provenance helpers are workflow utilities, not certified complete systematic-review engines.
Core features (v0.3 baseline, retained in v0.5.1)
MCP tool | Status / guarantee |
| OpenAlex, Europe PMC, Crossref concurrent metadata search, DOI deduplication, provider error reporting. Search is non-exhaustive. |
| Crossref metadata, relations, publisher links. |
| Exact normalized DOI/title metadata match, NOT content verification. |
| Crossref |
| Europe PMC/PMC XML for supplied PMCID; records section/paragraph-span IDs, offsets, XML and paragraph SHA-256, and truncation. No PDF page claims. |
| Fetches Europe PMC JATS XML and returns direct matching paragraph IDs, section, and hashes; no scientific validity verdict. |
| Deterministic literal text presence only. Does not prove scientific claim. |
| Transparent keyword/phrase screening; NOT risk-of-bias evaluation. |
| Outcome-specific source-anchored HUMAN-SUPPLIED annotation validation. Flags untraceable/contradictory evidence; never infers formal RoB2/ROBINS-I judgments. |
| Fetches Europe PMC full-text JATS XML by PMCID and independently anchors human annotations to exact paragraphs with source SHA-256; handles truncated sources explicitly. |
| Screens user-supplied p values, sample sizes and CI range inconsistencies; does NOT recompute analyses. |
| Metadata comparison, NOT conflicting results inference. |
| Publisher-registered Crossref links; cannot guarantee raw data/code. |
| Validates explicit user-supplied nodes and evidence-referenced edges. No inferred evidence. |
| Timestamped multi-provider search log; NOT PRISMA screening. |
| Append local hash-chained JSONL evidence record with cross-process file locking. |
| Integrity check detects modified rows; cannot detect wholesale replacement/truncation without an external signed anchor. |
Related MCP server: paper-search-mcp
Install and run
Requires Python 3.11 or later.
python -m pip install literature-evidence-mcp
literature-evidence-mcp # stdio; no terminal output is expectedTo work on the source instead:
python -m venv .venv
. .venv/bin/activate # Linux/macOS
# Windows PowerShell: .\.venv\Scripts\Activate.ps1
python -m pip install -e '.[dev]'
pytest -q
literature-evidence-mcp # stdio; no terminal output is expectedLocal HTTP (do not expose to the Internet without an authenticated proxy):
MCP_TRANSPORT=streamable-http MCP_PORT=8000 literature-evidence-mcp
# MCP endpoint: http://127.0.0.1:8000/mcpConfigure your MCP client to execute literature-evidence-mcp as a local subprocess. SDK: MCP Python v2.
OpenAlex basic queries can be keyless but have a restrictive daily budget. Obtain a key from OpenAlex and set OPENALEX_API_KEY for regular use. Environment variables are not committed.
Scientific integrity and constraints
Exact / proxy / unknown: tools distinguish bibliographic facts, text matches, and method-term proxies from scientific validation. All uncertain scientific conclusions remain
NOT_VERIFIED/SCREENING_ONLY.Never interpret zero search results as evidence a paper does not exist. Providers may be unavailable, rate-limited, incomplete or stale.
Crossref retraction check is a metadata check, not a global clearance certificate.
No unrestricted URL retrieval: fixed trusted origins and API paths, DOI and PMCID validation, request timeouts, streaming response-size limits, bounded retries.
Raw bibliographic responses are not persisted unless explicitly passed into
export_evidenceor throughlog_review_search.Full-text reuse and redistribution are controlled by source/publisher licenses; this server does not download arbitrary PDFs or bypass access controls.
Hash-chain is not independently authenticated; keep external checkpoints if you need tamper-evidence against complete log replacement. v0.3 and later serialize writers across processes using a local lock file; they cannot guarantee atomic behavior on all network filesystems.
Current limitations and roadmap (NOT YET IMPLEMENTED)
Evaluate API coverage/precision against independently labeled benchmark queries and monitor API drift.
Licensed PDF retrieval/redistribution and verified figure/table contents; v0.5 adds bounded caller-supplied PDF page text, table and image object provenance but does not fetch or redistribute PDFs.
Human-supervised formal RoB 2, ROBINS-I, GRADE; v0.3 adds cited annotation traceability and numerical field screens but NOT validated risk judgments or statistical reproduction.
Citation graph with independently verified edge provenance; v0.5 adds caller-supplied edge traversal and Crossref notice propagation, but edges and notices remain provider-asserted.
Full two-stage PRISMA 2020 retrieval, study-level inclusion/adjudication and report export; v0.5 adds caller-supplied two-reviewer screening records and checklist/identification accounting.
Audited quantitative extraction/meta-analysis with independent statistical tests and uncertainty.
API rate accounting, request queueing, persistent cache, integration/security hardening and authenticated hosting.
Obtain a blind expert-labeled retrieval and risk-of-bias test set; current ROBoto2 excerpt-match audit and 3-query competitor smoke cannot prove accuracy superiority.
v0.3 evidence audit and external evaluations
17 MCP tools (3 new:
audit_methodology,audit_pmc_methodology,check_statistical_reporting).External ROBoto2 benchmark: 174 of 413 delimited expert quote excerpts were located verbatim in PDF-parsed article text across 93 studies (42.13%); 0/413 rotated control matches. This is NOT bias-judgment or scientific accuracy; quoted reviewer notes and PDF parses can differ. Dataset licensing not verified; raw dataset is not redistributed. See benchmark protocol and aggregate report.
Same-query, same-provider retrieval smoke tests comparing this MCP, Athenaeum, and Paper Search MCP are recorded in competitor audit and
reports/live-*.json. Counts and times are not expert relevance metrics, and no performance dominance is asserted.
Testing
Offline deterministic tests mock every external provider and check concurrent ledger writers, covering DOI validation, error handling, failure isolation, ambiguous status reporting, ledger corruption, method-screening caveats and evidence graph validation.
Verification: On 2026-10-18, 20 baseline v0.2 tests passed with the real MCP v2 SDK in a connected development environment, including in-process MCP tool discovery/call. The opt-in python scripts/live_smoke.py also passed for OpenAlex, Europe PMC and Crossref. CI does not run live provider checks. Hosted Streamable HTTP, production resilience, source accuracy, formal risk-of-bias validity, and competitive superiority have NOT been independently verified.
Executed live competitor search and prospective expert-review preparation
19 October 2026 same-query live comparison ran the project, Athenaeum and Paper Search MCP on the same three historical queries, capped at five hits from each of OpenAlex/Crossref/Europe PMC. Returned counts were respectively 43/45/44 (DOI-bearing 38/41/39). Counts and overlap are not relevance, retrieval precision, or verified scientific superiority, and an opponent can suppress provider failures.
Scope: both scientific literature retrieval and scientific evidence assessment across all research disciplines, not neuroscience or biomedicine alone. Mathematics, physics, chemistry, biology, astronomy, computer science and other fields are eligible; their independent domain-specific expert review and scientific criteria remain to be specified.
The new general-science expert-blind protocol adds an operational, label-free packet writer with separate HMAC-keyed private identity mapping and fail-closed synthetic tests. No new human gold, independent reviewers, adjudication or prospective blind test occurred. Primary scientific decisions await user authorization; no default NLI or other scientific model was changed.
Completed fixed-corpus NFCorpus exploratory retrieval evaluation
The two-public-dataset exploratory report
contains NFCorpus 323-query fixed-corpus BM25 measurements, using the
pre-existing BM25Okapi implementation without changing default MCP behavior.
Known-positive Recall@10 was 14.49%, first-known-positive MRR@10 was
0.512, and 25/323 queries had no lexical overlap. These measure different
properties, and no external competitor was compared. Other public tests
remain retrospective, not independent prospective validation.
The full public VitaminC evaluation used 55,197 source pairs on the existing three pinned NLI checkpoints: original DeBERTa-small 54.69% accuracy, FEVER/ANLI-base 60.18%, and general DeBERTa-base 58.20%. Important negative result: FEVER/ANLI-base REFUTE recall 41.95% is below the original small model's 57.88%. All results remain exploratory; no production/default change or statistically confirmed scientific win.
Pinned independent-test candidates (no gold unblinding)
The candidate source and license audit records initial immutable integrity checks for BEIR NFCorpus biomedical retrieval and VitaminC three-way Wikipedia fact-checking. The source-pin stage verified bytes before opening test labels; subsequent exploratory runs did evaluate the public test labels and are documented separately. These public benchmarks are not prospectively blinded, and possible pretraining/test leakage is unresolved. This historical biomedical and Wikipedia evaluation does not limit the general-science project scope. No independent expert-labeled head-to-head superiority is claimed.
Two-track head-to-head scientific comparison (offline audit)
The frozen-input two-track comparison harness separately examines retrieval of known relevant papers and SUPPORT / REFUTE / INSUFFICIENT evidence decisions on identical case IDs across two or more real system outputs. It requires pinned gold/prediction SHA-256 and retains NULL/MIXED/BLOCKED/ERROR, missing positive labels, and negative results. Existing historical SciFact, HealthVer, HealthFC and competitor smokes remain exploratory: none proves independent blinding or general superiority. The harness intentionally does not choose a primary metric, winner, or significance test without an approved scientific protocol.
Extended discovery and citation chain (35 MCP tools)
Two optional, provenance-conscious tools strengthen bibliographic exploration:
search_literature_extended queries OpenAlex, Europe PMC, Crossref and
Semantic Scholar concurrently; each source's errors and disagreements are
preserved, and missing/invalid DOI records are never silently merged by title.
expand_citation_chain performs bounded 1–2 hop forward/backward OpenAlex
citation traversal with fixed request and node caps, explicit partial states,
and source-identified, provider-asserted edges. Neither tool ranks or
scientifically validates research, and neither claims exhaustive search. The
original three-provider search_literature behavior is unchanged.
Semantic Scholar may return HTTP 429 without an optional API key; the
optional tool explicitly reports RATE_LIMITED and the HTTP code. Citation
traversal now fails closed on an OpenAlex seed DOI mismatch or missing DOI.
Protocol, examples, hard limits and verification.
Bibliographic export (MCP tool 14 of 35)
The offline, opt-in export_bibliography MCP tool converts supplied citation metadata
to BibTeX, RIS or CSL-JSON, with injection-safe escaping, explicit DOI
syntax/verification separation, missing-field honesty and conflict flags. It
closes an earlier documented reference-export feature gap without adding a
source provider or asserting scientific accuracy. See
reference export and reproducibility.
No Zotero sync/account integration and no npm Registry release.
License and contributions
Apache-2.0. See LICENSE, CONTRIBUTING.md, SECURITY.md. Neither the license nor this repository grants rights to republish third-party scientific articles.
Documentation references
v0.2 technical change log
Added direct full-text quote provenance (
verify_source_quote), explicit section and paragraph IDs, UTF-8 text hashes and truncation indicators.Replaced unbounded HTTPX body buffering with a streamed 2 MB JSON / 4 MB XML response cap.
Serialized evidence writes across independent callers/processes using
filelockandasyncio.to_thread; the ledger still requires independently stored checkpoints for stronger guarantees.Added regression tests for nested sections, source offsets, missing quotations, oversized responses and concurrent writers.
Scientific limits remain: matching text is not proof, keyword methodology screening is not a formal bias assessment, and no independent competitor benchmark has been performed.
v0.3 technical change log
Real Europe PMC XML paragraph source-bound annotation audit, distinguishing incomplete retrieval from proven absence; never claims RoB2 assessment.
98 deterministic unit and protocol tests; 100% Python statement and branch coverage on local Python 3.12, including error paths. GitHub CI enforces 100% across Python 3.11, 3.12 and 3.13.
Human-supplied outcome-specific methods evidence traceability; unknowns and contradictions explicit.
Mechanical checks for invalid p-values, sample sizes and interval bounds; no fabricated inferential statistics.
Pinned external ROBoto2 research benchmark with aggregate report, licensing caveat and non-comparable RoB category warning.
Three-engine public-provider retrieval smoke and evidence-based competitor feature matrix; no claimed superiority.
Coverage policy (strict)
The CI workflow runs the complete deterministic suite with both statement and branch coverage. The fail-under threshold is 100% across all packaged Python code; no modules, files, functions, or error paths are excluded via coverage omit directives or pragma flags. Code changes must add executable tests covering every new line and branch before merging. Coverage is not equivalent to scientific or statistical validity.
Reproduce locally:
pytest -q --cov=literature_evidence_mcp --cov-branch --cov-report=term-missing --cov-fail-under=100v0.3.1: live full-text negotiation and guarded literal citation matching
Fixed Europe PMC
fullTextXMLHTTP content negotiation: XML requests useAccept: application/xmlinstead of the JSON default, which previously produced406 Not Acceptablein live calls. Live smoke on 2026-10-18 retrieved 47 XML paragraphs fromPMC7121925and verified a sourced paragraph quote; external API availability may change.Aligned quoted-text checks across
verify_claim,verify_source_quoteand methodology audits. Case-insensitive and whitespace-flexible comparison now requires intact Unicode word boundaries where a quoted token begins or ends with a word character. The wordsignificantcan no longer be verified frominsignificant, noreffectivefromineffective. Punctuation in quoted snippets remains literal.Both direct-text and Europe PMC JATS quote lookups return start/end character offsets (direct text or local paragraph) and source hashes; absence from truncated XML is explicitly marked
NOT_VERIFIED_SOURCE_TRUNCATED. No claim of scientific validity or inferred method quality is introduced.The GitHub CI gate remains 100% statement AND branch coverage on Python 3.11, 3.12 and 3.13; no coverage exclusions.
v0.3.2: strict work identity guards for literature search
Search results now normalize DOI text using the same validated canonical syntax as direct DOI lookups. DOI URL prefixes and case variants are normalized before merging provider records.
SYNTAX_VALID_NOT_RESOLVEDexplicitly means the DOI shape passed validation, not that the DOI or scientific claim was independently resolved.Untrusted provider DOI values that fail validation are preserved as
doi_rawwithdoi_status=INVALID_PROVIDER_DOI_NOT_RESOLVED, while the normalizeddoivalue isnull. No cross-provider aggregation is performed on invalid DOI strings.Work records with no DOI are kept separate, even when providers report identical titles or the same provider returns repeated titles. Their
doi_status=MISSINGdenotes missing evidence of work identity, not evidence that no DOI exists.Provider disagreements and source provenance from v0.3.1 remain visible. No metadata consistency check or DOI format validation is a scientific truth verdict.
Quality gate unchanged: 100% statement and branch coverage across Python 3.11, 3.12 and 3.13, including DOI normalization and all error paths.
Node.js / TypeScript MCP adapter (v0.5.1)
An optional TypeScript v2 MCP stdio front end is available under packages/npm. It dynamically discovers the Python server's available MCP tools (35 in v0.5.1), forwards their input schemas and result/error statuses unchanged, and keeps all scientific decisions in the Python core. It provides a Node/npm integration point without rewriting or duplicating the scientific methodology. Both Python and Node.js are required; this is not a standalone TypeScript scientific engine.
From a checked-out repository:
python -m pip install -e .
npm install --prefix packages/npm
npm run --prefix packages/npm build
LITERATURE_EVIDENCE_PYTHON=python3 node packages/npm/dist/cli.jsWindows users should point LITERATURE_EVIDENCE_PYTHON to their installed Python executable. The npm package is prepared for publication; a successful npm registry publication is not implied by CI success. The Python test gate remains 100% statement/branch coverage; a separate Node.js CI job checks real client-to-Python MCP protocol behavior and 100% TypeScript line/branch/function coverage, plus package packing. The opt-in Rust text matcher was added in v0.4 (not in the original TypeScript adapter release).
Parallel native accelerators / numerical component (v0.4)
Three independently developed components are available in native/rust_text, native/go_sources and native/cpp_meta. Their explicit MCP endpoints are rust_locate_quote, go_parallel_provider_status and cpp_fixed_effect_meta. They are optional: an unavailable component returns NATIVE_NOT_INSTALLED, and the original Python scientific pipeline remains unchanged. The TypeScript MCP bridge dynamically discovers the now 35 Python tools. There is NO npm registry publication in this change.
Rust matches source text, not research claims. Go probes availability of three fixed API endpoints concurrently, not research quality. C++ computes fixed-effect inverse-variance pooling from supplied effects and standard errors; it does not establish study eligibility, homogeneity, bias control or causal validity. Details: native module instructions.
Quality rules: the existing Python/TypeScript CI retains 100% statement and branch coverage. Rust enforces 100% executable-source-line coverage, Go combines instrumented unit tests and the real CLI for 100% statements, and C++ enforces 100% executable-source-line coverage while excluding only noncode-only braces from GCC's mapping (explicitly reported). All native modules have distinct integration CI jobs; no scientific superiority is claimed.
v0.5 Review-workflow and analytical additions
35 MCP tools include new two-reviewer human RoB 2 / ROBINS-I V2 judgment records, GRADE domain recordkeeping, two-reviewer screening, PRISMA 2020 checklist (42 reporting rows)/identification accounting, bounded supplied PDF page text and table/image object provenance, Crossref notice propagation without mislabeling citing papers, and C++ DerSimonian-Laird random-effects and leave-one-out numerical calculations. Go now retrieves bounded real metadata with a local TTL cache and five-second batch request gate.
These tools are workflow and numeric helpers: clinical methodological accuracy, full PRISMA compliance, image/table contents and scientific truth are NOT automatically established. See docs/review-science-coverage.md.
The CI enforces 100% Python statement/branch coverage, 100% TypeScript line/branch/function coverage, strict Rust/Go/C++ native gates, plus Windows and macOS native build checks. No npm registry publication.
External independent labeled benchmark (SciFact + EvidenceBench)
Scientific superiority was not demonstrated. The new pinned, reproducible external gold evaluation runs SciFact's labeled dev claims and EvidenceBench's 293-paper original test set, with source SHA-256 hashes, training-only lexical threshold selection, documented independent rank-bm25 and lexical baselines, paper/claim-cluster bootstrap confidence intervals, and explicit absence of semantic claim predictions. Original raw copyrighted/licensed papers and annotations are NOT stored in the repository. CI recreates both published aggregated reports byte-for-byte. No npm registry publication is performed.
Open-corpus SciFact retrieval evaluation
A separate full-corpus evaluation protocol measures independent BM25 and lexical retrieval across all 5,183 SciFact abstracts. The historical benchmark did not modify the scientific MCP; a separate opt-in local BM25 candidate ranker is now available. No unsupported science-accuracy claims are made. Aggregated results are persisted as GitHub CI artifacts and are not published to npm.
Optional BM25 evidence candidate ranking (MCP tool 33 of 35)
bm25_rank_evidence uses rank-bm25 to
rank caller-supplied paper titles and abstracts. It is not invoked by the
existing scientific methods, does not fetch publications, and cannot verify a
paper's authenticity or whether a scientific claim is supported. The
dependency is installed only by explicit choice:
python -m pip install -e '.[retrieval]'Without that optional extra, the tool remains discoverable but returns
OPTIONAL_BM25_NOT_INSTALLED. No automatic installation or npm publication
takes place. See usage, input restrictions and scientific cautions.
Experimental offline claim/evidence NLI (MCP tool 34 of 35)
An explicitly optional, not clinically validated three-way
nli_assess_evidence MCP tool evaluates whether a caller-supplied passage
appears to support, refute or provide insufficient model evidence for a
claim. The pinned, SHA-256-verified DeBERTa NLI model runs offline and never
modifies the existing source-search/quote-verification or RoB/PRISMA/GRADE
workflow. Without a configured model it abstains.
Independent SciFact DEV audit (338 gold rationale sets): 39.1% non-abstaining coverage, 83.3% conditional accuracy on 132 decided examples, and 32.5% correct over all 338 when abstentions count as not correct. A train-majority unconditional baseline scored 63.9%, so no full-coverage superiority was demonstrated. The SciFact evaluation has no independent insufficient-evidence class and was given gold source rationales; neither scientific reliability nor end-to-end retrieval performance is established.
Full scientific protocol, reproducibility and limitations.
Optional local dependency: pip install -e '.[nli]'. No npm publication.
HealthVer three-class scientific validation (external held-out labels)
The opt-in NLI tool was evaluated without HealthVer fine-tuning or test threshold selection on the 1,823 human-labeled HealthVer TEST pairs: 46.57% three-way accuracy; macro-F1 38.42%; neutral F1 58.83%. SUPPORT recall was only 8.20%. On 1,694 unique claim–evidence pairs, accuracy dropped to 43.09%. An always-majority baseline selected using TRAIN scored 39.88%, so the test does not establish clinically reliable fact verification or scientific superiority. Both neutral predictions and low-confidence abstentions count as NEUTRAL for this limited benchmarking task; they are not proof of insufficient evidence.
A frozen-model error audit finds 1,447 raw NEUTRAL-argmax cases, including 540 gold SUPPORT and 269 gold REFUTE errors. The uncalibrated model also has ECE 0.493. These are not problems fixed by the optional module's existing thresholds; no model or production decision rule was changed.
Full HealthVer test methodology, class confusion and repeat-sensitivity analysis. The raw HealthVer data and large model weights are never published to the repository.
Explicitly selected experimental NLI alternatives (MCP tool 35 of 35)
Two additional pinned third-party NLI checkpoints are now available
only through an explicitly selected, local, offline
nli_assess_challenger_evidence challenger tool, with model files,
tokenizer and configuration SHA-256 validated.
The current scientific model and original tools are unchanged.
Exploratory HealthVer comparison: FEVER/ANLI DeBERTa-base had 48.99% accuracy and 41.67% macro-F1 versus original 46.57% and 38.42%; its SUPPORT recall remained only 14.01%. SciFact oracle-rationale classification also improved. Previously examined datasets are not sufficient to select a production winner. Neither alternative is clinically reliable or a scientific truth verifier.
Two-dataset protocol, test artifacts, and opt-in usage.
A third, explicitly exploratory HealthFC syntax-only question normalization audit uses only 511 conservatively transformed questions; 239 are excluded and meaning equivalence is not expert-verified. On this unreviewed subset, FEVER/ANLI accuracy was 70.25% versus original 59.30%; this is not confirmatory superiority. Original/transformed CC BY-NC-ND texts are not published. No npm registry publication.
Related projects
Part of the Furox scientific-computing portfolio: independently versioned projects that pair agent-facing interfaces (MCP servers and Agent Skills) with deterministic, fail-closed verification.
scientific-computing-system — zero-dependency Python numerics with run manifests.
scientific-computing-system-2.0 — NumPy/SciPy/pandas build with replayable fit records.
scientific-toolkit — MCP gateway over nine research tools.
axiomize — unit-checked modeling engine with SBML, CellML and Modelica export.
axiomize-quantum-skills-2.0 — modeling engine plus quantum-inspired reasoning bundle.
quantum-reasoning-skill — agent skill that keeps competing hypotheses alive.
plan-auditor — evidence-based completion gate for coding agents.
nomosguard — deterministic security decision layer with a hash-chained ledger.
eq-layer — interaction-policy layer that decides how an agent speaks.
repocraft — byte-deterministic project scaffolding.
Available Tools
35 toolsassess_methodologyC
Transparent phrase screening only; NOT a RoB-2, GRADE, or statistical audit.
Inputs: source_id (required), source_text (required).
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.
Inputs: outcome (required), study_id (required), annotations (required), source_text (required), +1 more.
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.
Inputs: pmcid (required), outcome (required), annotations (required), study_design (required).
bm25_rank_evidenceC
Opt-in BM25 of caller-supplied abstracts; never certifies scientific support.
Inputs: query (required), documents (required), top_k.
build_evidence_graphC
Validate user-supplied evidence graph with traceable evidence identifiers.
Inputs: edges (required), nodes (required).
check_retractionB
Inspect Crossref update-to and Retraction Watch-linked updates; absence is inconclusive.
Inputs: doi (required).
check_statistical_reportingA
Find mechanically inconsistent p values/CIs/sample-size entries, not test results.
Inputs: records (required).
compare_studiesC
Compare supplied bibliographic metadata; no inferred theoretical disagreements.
Inputs: papers (required).
cpp_fixed_effect_metaC
Opt-in C++ fixed-effect numerical pooling; heterogeneity/bias not assessed.
Inputs: studies (required).
cpp_random_effectsC
DerSimonian-Laird, Q, I², tau², approximate interval and leave-one-out.
Inputs: studies (required), leave_one_out.
crossref_update_alertsC
Fetch Crossref publication notices and flag citation descendants for review.
Inputs: dois (required), edges (required).
expand_citation_chainC
Bounded OpenAlex citation links, forward/backward; edges remain unverified metadata.
Inputs: seed_doi (required), max_depth, directions, max_per_direction.
export_bibliographyB
Export supplied metadata as BibTeX/RIS/CSL-JSON; NOT scientific verification.
Inputs: papers (required), output_format.
export_evidenceC
Append a JSON evidence record to local hash-chained JSONL ledger.
Inputs: kind (required), payload (required).
find_data_and_codeB
Find Crossref links to supplements/data/software, if registered; do not fetch them.
Inputs: doi (required).
get_paperA
Get Crossref DOI metadata and source links; does NOT validate scientific conclusions.
Inputs: doi (required).
go_literature_recordsC
Opt-in Go metadata retrieval, local cache and five-second request gate.
Inputs: query (required), limit, ttl_seconds.
go_parallel_provider_statusC
Opt-in concurrent Go status probe for three fixed literature APIs.
Inputs: query (required), limit.
log_review_searchC
Search + log reproducible search records; NOT an exhaustive systematic review.
Inputs: query (required), limit_per_source.
nli_assess_challenger_evidenceC
Explicitly selected, locally pinned experimental NLI; never scientific proof.
Inputs: claim (required), evidence (required), candidate (required), source_id (required).
nli_assess_evidenceC
Offline pinned NLI support/refute/insufficient MODEL estimate; never verified truth.
Inputs: claim (required), evidence (required), source_id (required), margin, +1 more.
pdf_page_provenanceD
User-supplied PDF: page hash, quote offsets, table and image bounding boxes.
Inputs: quote (required), pdf_base64 (required), page_number (required).
prisma_dual_screenD
Two independent reviewer screening decisions and one-stage PRISMA flow counts.
Inputs: records (required).
prisma_review_flowD
Auditable PRISMA identification/screening and explicit missing full-text stages.
Inputs: records (required), checklist (required), identified (required).
propagation_alertsC
Source-linked correction/retraction alerts without treating citations as retractions.
Inputs: edges (required), nodes (required), notices (required).
read_fulltextA
Read OA full-text XML by PMCID from Europe PMC, with source hash and truncation flag.
Inputs: pmcid (required), max_chars.
record_gradeC
Record human GRADE reasoning without inferring a validated certainty score.
Inputs: up (required), down (required), design (required), outcome (required), +2 more.
record_risk_of_biasC
Record two human RoB2/ROBINS-I V2 Nov-2025 appraisals, flag disagreements.
Inputs: outcome (required), study_id (required), framework (required), reviewers (required), +1 more.
rust_locate_quoteC
Opt-in Rust PyO3 literal quote match, no interpretation of scientific meaning.
Inputs: quote (required), source_text (required).
search_literatureC
Search OpenAlex, Europe PMC, Crossref; deduplicate DOI and report each provider error.
Inputs: query (required), limit_per_source.
search_literature_extendedC
Search four sources, including optional Semantic Scholar; never claim exhaustive recall.
Inputs: query (required), limit_per_source.
verify_citationB
Verify bibliographic DOI/title match in Crossref (not validity of the publication).
Inputs: doi (required), claimed_title (required).
verify_claimB
Check literal quote presence. This cannot scientifically verify a claim.
Inputs: quote (required), source_id (required), source_text (required).
verify_evidence_ledgerA
Check local JSONL ledger integrity; cannot detect replacement of the entire ledger.
Inputs: no named parameters.
verify_source_quoteB
Retrieve Europe PMC full text and locate quote in source paragraphs; NOT a scientific verdict.
Inputs: pmcid (required), quote (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
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.
Maintenance
Related MCP Connectors
Search and cite research claims with their evidence and reliability scores; publish claimsets.
Academic literature search, retrieval, and private library management on top of OpenAlex.
Citation and retraction checker for AI agents. Give it DOIs, PubMed or arXiv ids and it says whether each paper exists and whether it was retracted, withdrawn or corrected, using Crossref and Retraction Watch. It also searches publisher articles and open research papers, shows the x402 price in USDC an agent pays to read or cite each one, and traces a passage to the page it was copied from. Free, read-only, no account.
Search arXiv/Semantic Scholar/OpenAlex + medical evidence (PubMed/Europe PMC) + LaTeX/PDF tools.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables traceable scholarly literature reviews using free APIs, generating reports where every claim links to evidence IDs.MIT
- AlicenseAqualityDmaintenanceEnables searching scholarly literature across CrossRef, ERIC, Semantic Scholar, and OpenAlex, and retrieving open-access PDFs via Unpaywall.9MIT
- AlicenseAqualityBmaintenanceEnables scientists and their AI agents to check quoted passages against pinned open-access PubMed Central full texts, look up retraction status from PMC and Crossref, and run recorded literature searches. Every quote check, search and annotation is written to an append-only, hash-chained log that can be verified, giving a dated record of what was searched and found.7MIT
- AlicenseAqualityCmaintenanceEnables keyless, read-only literature research by searching OpenAlex, Crossref, Europe PMC, PubMed and arXiv at once, merging and ranking results, following citations, retrieving open-access full text, looking up clinical trials, verifying citations, and exporting BibTeX, RIS or CSL-JSON without any accounts or API keys.102MIT