Biologist MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BIOLOGIST_DEBUG | No | Enable debug logging. Default: false | false |
| BIOLOGIST_API_TOKEN | No | Optional Bearer Token for protected endpoints. | |
| BIOLOGIST_TIMEOUT_MS | No | Request timeout in milliseconds. Default: 60000 | 60000 |
| BIOLOGIST_API_BASE_URL | No | Base URL for the Biologist Rails API (v1). Default: http://localhost:3000/api/v1 | http://localhost:3000/api/v1 |
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": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| searchC | Unified cross-catalog semantic or keyword search across species and individual organisms in the Biologist comparative biology manifold. |
| find_counterpartsA | Find nearest ecological counterparts or convergent evolutionary analogs to a specified species or organism using 1024-dimensional pgvector cosine distance. |
| list_biomesB | List biomes (global ecosystems, climatic zones, and primary environmental regimes) registered in Biologist with species counts. |
| get_biomeA | Retrieve details of a single biome including its member species. |
| create_biomeC | Create a new biome record in the catalog. |
| update_biomeC | Update an existing biome's name or description. |
| delete_biomeA | Delete a biome and its cascaded species and organisms. |
| upsert_biomes_batchB | Batch insert or update biomes matching case-insensitively on name. |
| populate_biomesB | Trigger LLM discovery to populate major global biomes and environmental regimes. |
| populate_biome_speciesC | Discover and populate canonical species for a specific biome via LLM generation. |
| list_speciesB | List species registered in Biologist with filtering by biome, themes, embedding status, and search keywords. |
| get_speciesB | Retrieve details of a single biological species including its biome and child organisms. |
| create_speciesC | Create a new species record under a parent biome. |
| update_speciesC | Update an existing species's attributes, biome assignment, or themes. |
| delete_speciesB | Delete a species and its associated individual organisms. |
| generate_species_embeddingB | Generate or refresh the 1024-dimensional semantic embedding for a species. |
| populate_species_organismsC | Discover and populate individual organisms, castes, or morphs for a specific species via LLM generation. |
| populate_species_bulkB | Trigger LLM discovery to populate species across all registered biomes. |
| upsert_species_batchB | Batch insert or update species scoped to a specific biome matching case-insensitively on name. |
| list_organismsB | List individual organisms (morphs, castes, sexual dimorphisms, life-history stages) with filtering by species, biome, themes, and embedding status. |
| get_organismA | Retrieve details of a single individual organism including parent species and biome. |
| create_organismC | Create a new individual organism/morph record under a parent species. |
| update_organismC | Update an existing organism's attributes, species assignment, or themes. |
| delete_organismC | Delete an individual organism record. |
| generate_organism_embeddingB | Generate or refresh the 1024-dimensional semantic embedding for an individual organism. |
| populate_organisms_bulkB | Trigger LLM discovery to populate individual organisms across all registered species. |
| upsert_organisms_batchB | Batch insert or update organisms scoped to a specific species matching case-insensitively on name. |
| compute_clustersB | Compute live connected-components vector clusters for Species or Organisms across biomes without modifying the database. |
| create_cluster_snapshotA | Compute connected-components clustering and freeze it immediately into an immutable database snapshot. |
| list_cluster_snapshotsC | List frozen archetype cluster snapshots in Biologist. |
| get_cluster_snapshotC | Retrieve details of a frozen cluster snapshot including member groups and generated synthesis reports. |
| delete_cluster_snapshotB | Delete a frozen cluster snapshot along with its cascaded cluster groups and synthesis reports. |
| list_cluster_groupsC | List all archetype cluster groups belonging to a specific frozen snapshot. |
| get_cluster_groupA | Retrieve details of a specific archetype cluster group with all member species or organisms. |
| list_cluster_reportsC | List generated multi-phase comparative biology and ecological manifold synthesis reports. |
| get_cluster_reportB | Retrieve complete scholarly biological report content, progress percentage, markdown monograph, and intermediate summaries. |
| create_cluster_reportC | Initiate a 2-Phase Map-Reduce synthesis report on a frozen cluster snapshot. |
| delete_cluster_reportA | Delete a synthesis report along with its intermediate summaries and sub-reports. |
| generate_deep_synthesisB | Initiate a 3-Phase Hierarchical Deep Synthesis monograph, reusing Phase 1 summaries from a completed parent report. |
| list_report_summariesB | List all Phase 1 per-cluster analyses belonging to a synthesis report. |
| get_report_summaryC | Retrieve a single Phase 1 per-cluster scholarly summary. |
| list_report_sub_reportsB | List all Phase 2 intermediate batch analyses belonging to a detailed synthesis report. |
| get_report_sub_reportC | Retrieve a single Phase 2 batch analysis. |
| list_jobsB | List recent asynchronous background jobs (embedding calculations, LLM discoveries, synthesis reports). |
| get_job_statusB | Check the status, progress, and result of an ActiveJob/Sidekiq background task. |
| wait_for_jobA | Poll a background job until completion or failure with configurable timeout. |
| get_platform_statusA | Get overall platform health, catalog entity counts, embedding coverage stats, and active LLM configuration. |
| get_settingsA | Get embedding completion metrics for Species and Organisms, active embedding/LLM parameters, and context window presets. |
| update_context_windowC | Dynamically update the active LLM context window token size. |
| trigger_bulk_embeddingsC | Enqueue bulk embedding generation for all Species or Organisms. |
| get_openapi_specA | Retrieve the raw OpenAPI 3.1 specification for the Biologist API. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| comparative_biological_analysis | Prompt template for comparing two biological species or organisms across biomes using morphological traits, trophic strategies, and semantic manifold distance. |
| biological_cluster_monograph | Prompt template to draft an academic biological treatise based on Biologist archetype clusters and frozen snapshots. |
| evolutionary_convergence_inquiry | Prompt template for investigating convergent evolutionary adaptations across disparate biomes. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| platform-status | |
| biomes-catalog |
TDQS
Scored across 51 tools
The tool set is organized by resource, but several tools have overlapping boundaries: get_platform_status and get_settings both expose embedding/LLM configuration, while create_*, upsert_*_batch, and populate_* provide three different creation paths for biomes, species, and organisms. report_summary/sub_report/cluster_report tools are distinguishable, but the sheer number of similarly named lifecycle tools increases misselection risk.
Most names follow a clear snake_case verb_noun pattern (list_biomes, create_species, delete_organism, generate_organism_embedding). There are minor deviations such as the bare 'search' and some noun-heavy report names, but the convention is generally predictable.
At 51 tools, the surface is heavy for any MCP server and includes many near-parallel CRUD, batch, populate, embedding, snapshot, reporting, job, and system tools. The domain is broad, but the count still feels excessive relative to the core workflow.
The server covers full CRUD lifecycles for biomes, species, organisms, cluster snapshots, and reports, plus embedding, job, search, and system operations. Minor gaps exist (for example, no direct update/delete for cluster groups, and snapshot immutability is intentional), but the main workflows are well supported.