Reactome MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_pathwaysC | Search for biological pathways by name, description, or keywords |
| get_pathway_detailsC | Get comprehensive information about a specific pathway |
| find_pathways_by_geneC | Find all pathways containing a specific gene or protein |
| find_pathways_by_diseaseC | Find disease-associated pathways and mechanisms |
| get_pathway_hierarchyC | Get hierarchical structure and parent/child relationships for a pathway |
| get_pathway_participantsC | Get all molecules (proteins, genes, compounds) participating in a pathway |
| get_pathway_reactionsC | Get all biochemical reactions within a pathway |
| get_protein_interactionsC | Get protein-protein interactions within pathways |
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 8 tools
Every tool has a clearly distinct purpose with no ambiguity. For example, find_pathways_by_disease and find_pathways_by_gene target different entry points, while get_pathway_details, get_pathway_hierarchy, get_pathway_participants, and get_pathway_reactions each focus on specific aspects of pathway information. The descriptions reinforce these distinctions, making misselection unlikely.
All tool names follow a consistent verb_noun pattern with snake_case, such as find_pathways_by_disease, get_pathway_details, and search_pathways. The naming is predictable and readable throughout the set, with no deviations in style or convention.
With 8 tools, the count is well-scoped for a biological pathway server. Each tool earns its place by covering distinct operations like searching, retrieving details, and analyzing components, without being overly sparse or bloated. This aligns with typical MCP server ranges of 3-15 tools.
The tool surface provides complete coverage for querying and exploring biological pathways. It includes search (search_pathways, find_pathways_by_disease/gene), retrieval (get_pathway_details, get_pathway_hierarchy), and analysis (get_pathway_participants, get_pathway_reactions, get_protein_interactions), with no obvious gaps that would cause agent failures in this domain.