MCP Server
Catalyst evidence graph
ai.catalystproject/evidence-graph
What this MCP does
Searches graded research findings and inferred biochemical relationships for compounds, outcomes, and proteins.
Capabilities
Tools
6
tools
get_finding
One finding, with its grade explained
One graded finding by its id (the last part of a permalink, /e/{id}): the claim, its grade and what that grade means, the verbatim quote, the study design and the paper. Use it to explain why a finding has the grade it has.
Read only
Idempotent
Input schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['finding_id'], 'properties': {'finding_id': {'type': 'string', 'pattern': '^[0-9A-HJKMNP-TV-Z]{26}$', 'description': 'A 26-character finding id, from a permalink or get_findings.'}}}
get_findings
Graded findings about a node
The curated, graded study findings for one node: for a compound, what it has been shown to affect; for an outcome, which compounds have been studied against it. Each finding carries a grade from A (well established) to F (speculative), the verbatim sentence it was drawn from, the paper, the population and dose, and a permalink. A grade describes evidence strength, not a recommendation. Always give the grade with the claim, and link the permalink. An empty list means nothing has been curated yet, not that the compound does nothing.
Read only
Idempotent
Input schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['node_id'], 'properties': {'limit': {'type': 'integer', 'default': 20, 'maximum': 50, 'minimum': 1, 'description': 'Findings to return, strongest grade first.'}, 'node_id': {'type': 'string', 'pattern': '^[A-Za-z_]+:[A-Za-z0-9_./+-]+$', 'maxLength': 120, 'minLength': 3, 'description': 'A node id from search_nodes, e.g. CHEBI:16919 (creatine).'}}}
get_reactions
Reactions a compound or protein takes part in (inferred)
Biochemical reactions from Rhea and Human-GEM that a compound is a substrate or product of, or that a protein catalyses or transports. Every row is assertion_class 'inferred': a reaction two public databases record, not a result anyone measured in a person. Present these as known biochemistry, never as an effect a compound has, and never as a recommendation. For effects, use get_findings. A compound flagged is_hub (water, ATP, protons and the like) returns its reaction count only, because it participates in nearly everything and a row list would not be biology anyone reads. Coverage: the whole of one Rhea release and one Human-GEM release, each reaction counted once; a participant that is not a node in this graph is listed but not linked, and only human enzymes that are nodes are listed at all. An empty result means no reaction in those releases names this node, not that the body has none.
Read only
Idempotent
Input schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['node_id'], 'properties': {'limit': {'type': 'integer', 'default': 25, 'maximum': 50, 'minimum': 1}, 'offset': {'type': 'integer', 'default': 0, 'maximum': 10000, 'minimum': 0}, 'node_id': {'type': 'string', 'pattern': '^[A-Za-z_]+:[A-Za-z0-9_./+-]+$', 'maxLength': 120, 'minLength': 3, 'description': 'A node id from search_nodes, e.g. CHEBI:16919 (creatine).'}}}
get_relations
Reference-database relations (hypotheses)
What public reference databases (Reactome, UniProt, Rhea, ChEBI and others) record about a node: transporters, enzymes, pathways, expression. Every row is assertion_class 'inferred': a hypothesis about how a compound could act, not a result anyone measured in people. Present these as possible mechanisms and never as effects. For effects, use get_findings.
Read only
Idempotent
Input schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['node_id'], 'properties': {'limit': {'type': 'integer', 'default': 25, 'maximum': 50, 'minimum': 1}, 'offset': {'type': 'integer', 'default': 0, 'maximum': 10000, 'minimum': 0}, 'node_id': {'type': 'string', 'pattern': '^[A-Za-z_]+:[A-Za-z0-9_./+-]+$', 'maxLength': 120, 'minLength': 3, 'description': 'A node id from search_nodes, e.g. CHEBI:16919 (creatine).'}, 'predicate': {'type': 'string', 'pattern': '^[a-z_]+$', 'maxLength': 40, 'description': 'Limit to one relation type, e.g. transports.'}}}
reach
What a compound can become, and through what (inferred, a hypothesis)
Breadth-first reachability through the reactions two public databases (Rhea, Human-GEM) record: what a compound could become, and through which reactions and enzymes, within up to 3 steps. Every route is assertion_class 'inferred': a hypothesis drawn from reference databases, never a measured or reported effect. Present it as known biochemical connectivity â never as an effect, a recommendation, or a claim that the body actually does this. For measured effects, use get_findings. Common cofactors and currency species (water, ATP, protons and the like) are excluded as intermediate steps, so a route never reads 'reaches everything through ATP'. A currency species is also never materialised as from_id or to_id itself â asking about one returns reachable: null with a coverage note explaining that, not a checked "0 routes". Give to_id to check one target compound; omit it to list everything from_id reaches. A route not being found can mean three different things, and the result's coverage field says which: reachability may not have been BUILT for this scope yet (nothing has been checked); it may have been checked and found NOT REACHABLE through the reactions loaded â never read that as "the body cannot make it"; or the compound asked about may be a currency species, structurally excluded rather than searched.
Read only
Idempotent
Input schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['from_id'], 'properties': {'depth': {'type': 'integer', 'default': 3, 'maximum': 3, 'minimum': 1, 'description': 'Longest route to consider, in reaction steps (1-3).'}, 'limit': {'type': 'integer', 'default': 25, 'maximum': 50, 'minimum': 1, 'description': 'Rows to return when to_id is omitted.'}, 'to_id': {'type': 'string', 'pattern': '^[A-Za-z_]+:[A-Za-z0-9_./+-]+$', 'maxLength': 120, 'minLength': 3, 'description': 'A target compound. Omit to list everything from_id reaches.'}, 'offset': {'type': 'integer', 'default': 0, 'maximum': 10000, 'minimum': 0}, 'from_id': {'type': 'string', 'pattern': '^[A-Za-z_]+:[A-Za-z0-9_./+-]+$', 'maxLength': 120, 'minLength': 3, 'description': 'The compound to start from.'}}}
search_nodes
Find a compound, outcome or protein
Search the Catalyst evidence graph by name or synonym (for example "magnesium glycinate", "sleep quality", "creatine"). Returns node ids to pass to get_findings or get_relations. It finds things; it does not say anything about them.
Read only
Idempotent
Input schema
{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['query'], 'properties': {'query': {'type': 'string', 'maxLength': 80, 'minLength': 2, 'description': 'A name, synonym or phrase.'}}}
History
Recent tool changes
Added
reach
Oct. 5, 2026, 2:40 a.m.
Added
get_reactions
Oct. 5, 2026, 2:40 a.m.
Added
get_relations
Oct. 5, 2026, 2:40 a.m.
Added
get_finding
Oct. 5, 2026, 2:40 a.m.
Added
get_findings
Oct. 5, 2026, 2:40 a.m.
Added
search_nodes
Oct. 5, 2026, 2:40 a.m.
Discover
Similar MCP servers
Pubmed
io.github.pipeworx-io/pubmed
Provides PubMed biomedical literature search and retrieval, including abstracts, full text where available, citation metadata, re…
Europepmc
io.github.pipeworx-io/europepmc
Searches and retrieves biomedical literature from Europe PMC, including abstracts, full records, citations, publication metadata,…
Chembl
io.github.pipeworx-io/chembl
Queries the ChEMBL drug-discovery database for molecules, mechanisms of action, indications, targets, and small-molecule bioactiv…
Biorxiv
io.github.pipeworx-io/biorxiv
Provides bioRxiv and medRxiv preprint metadata, publication status, and publisher lookups, alongside broader structured research …
Catnap
io.github.pipeworx-io/catnap
Searches LANL HIV immunology and CATNAP databases for antibody metadata, neutralization measurements, epitopes, binding sites, an…
Claidex MCP
com.claidex/failure-intelligence
Searches biomedical claims, clinical trials, drug databases, adverse-event data, literature, preprints, and failure-risk analyses.
raras
io.github.rarasAI/raras
Provides a source-grounded rare-disease knowledge graph covering diseases, phenotypes, genes, drugs, literature, clinical trials,…
Cure Cancer With AI
io.github.hifarrer/cure-cancer-with-ai
Provides oncology research, clinical trial, FDA approval, news, and compound data, along with biomedical predictions for toxicity…