Biologist MCP Server
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., "@Biologist MCP Server find species similar to the red fox, then synthesize the cluster report"
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.
Biologist Model Context Protocol (MCP) Server
A Model Context Protocol (MCP) server providing deep LLM-agent tool, resource, and prompt integrations with Biologist — an open-source computational research platform and quantitative analytical laboratory for comparative biology, ecology, and organismal taxonomy.
Overview
The biologist-mcp server enables AI agents (Claude Code, Cursor, Gemini CLI, Antigravity) to query, manipulate, cluster, and synthesize ecological and taxonomic domain models directly over standard input/output (stdio):
51 Registered MCP Tools across 8 functional modules (Search, Biomes, Species, Organisms, Clustering, Synthesis Reports, Background Jobs, and System Diagnostics).
4 Registered MCP Resources exposing read-only live platform status, catalogs, cluster snapshots, and markdown monographs.
3 MCP Prompt Templates for comparative biological studies, cluster synthesis monographs, and evolutionary convergence inquiries.
1024-dimensional semantic manifold querying via PostgreSQL
pgvectorHNSW indexes.
Related MCP server: AgentBase
Architectural Mapping
Tier / Domain | Model | Table Name | MCP Module / Tools |
Tier 1 | Biomes & Climatic Zones |
|
|
Tier 2 | Species & Keystone Taxa |
|
|
Tier 3 | Individual Organisms & Morphs |
|
|
Clustering | 15-Level Agglomerative |
|
|
Synthesis | Multi-Stage Map-Reduce |
|
|
Global Search | Cross-Catalog pgvector | Multi-table |
|
Platform | Jobs & System Info | Multi-service |
|
Installation & Setup
Prerequisites
Node.js 20+
Running instance of Biologist (
http://localhost:3000)
Build
git clone https://github.com/leouofa/biologist-mcp.git
cd biologist-mcp
npm install
npm run buildConfiguration
Environment Variables
Configure via .env file or export in your shell:
# Base URL for the Biologist Rails API (v1)
BIOLOGIST_API_BASE_URL=http://localhost:3000/api/v1
# Optional Bearer Token for protected endpoints
BIOLOGIST_API_TOKEN=
# Request timeout in milliseconds (default: 60000)
BIOLOGIST_TIMEOUT_MS=60000
# Enable debug logging
BIOLOGIST_DEBUG=falseCLI Options
biologist-mcp [options]
Options:
-u, --url <url> Biologist API base URL (default: http://localhost:3000/api/v1)
-k, --api-key <key> Optional API key / Bearer token
-t, --timeout <ms> Request timeout in milliseconds (default: 60000)
-d, --debug Enable debug logging
-h, --help Display this help messageMCP Client Configuration
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"biologist": {
"command": "node",
"args": ["/path/to/biologist-mcp/dist/index.js"],
"env": {
"BIOLOGIST_API_BASE_URL": "http://localhost:3000/api/v1"
}
}
}
}Antigravity
Add to your antigravity_config.json or MCP settings:
{
"mcpServers": {
"biologist": {
"command": "node",
"args": ["/path/to/biologist-mcp/dist/index.js"],
"env": {
"BIOLOGIST_API_BASE_URL": "http://localhost:3000/api/v1"
}
}
}
}MCP Resources
URI Template | MIME Type | Description |
|
| Real-time platform health, counts, and LLM configuration |
|
| Catalog of all registered biomes |
|
| Frozen cluster snapshot data with members and reports |
|
| Generated synthesis monograph in academic Markdown |
MCP Prompts
comparative_biological_analysis: Rigorous comparative analysis between two species or organisms using semantic manifold distance, trophic strategies, and functional adaptations.biological_cluster_monograph: Academic synthesis monograph prompt for drafting a formal treatise from frozen archetype clusters.evolutionary_convergence_inquiry: Cross-biome convergence analysis prompt investigating analog adaptations across independent lineages.
Testing
# Run test suite
npm test
# Run tests in watch mode
npm run test:watchLicense
This project is open-source software licensed under the MIT License.
Available Tools
51 toolscompute_clustersB
Compute live connected-components vector clusters for Species or Organisms across biomes without modifying the database.
Inputs: force, level, target_type, full_coverage.
create_biomeC
Create a new biome record in the catalog.
Inputs: name (required), description.
create_cluster_reportC
Initiate a 2-Phase Map-Reduce synthesis report on a frozen cluster snapshot.
Inputs: prompt (required), cluster_snapshot_id (required).
create_cluster_snapshotA
Compute connected-components clustering and freeze it immediately into an immutable database snapshot.
Inputs: level (required), title (required), target_type (required), full_coverage.
create_organismC
Create a new individual organism/morph record under a parent species.
Inputs: name (required), species_id (required), themes, description.
create_speciesC
Create a new species record under a parent biome.
Inputs: name (required), biome_id (required), themes, description.
delete_biomeA
Delete a biome and its cascaded species and organisms.
Inputs: id (required).
delete_cluster_reportA
Delete a synthesis report along with its intermediate summaries and sub-reports.
Inputs: id (required).
delete_cluster_snapshotB
Delete a frozen cluster snapshot along with its cascaded cluster groups and synthesis reports.
Inputs: id (required).
delete_organismC
Delete an individual organism record.
Inputs: id (required).
delete_speciesB
Delete a species and its associated individual organisms.
Inputs: id (required).
find_counterpartsA
Find nearest ecological counterparts or convergent evolutionary analogs to a specified species or organism using 1024-dimensional pgvector cosine distance.
Inputs: id (required), entity_type (required), limit, threshold.
generate_deep_synthesisB
Initiate a 3-Phase Hierarchical Deep Synthesis monograph, reusing Phase 1 summaries from a completed parent report.
Inputs: report_id (required), batch_size.
generate_organism_embeddingB
Generate or refresh the 1024-dimensional semantic embedding for an individual organism.
Inputs: id (required), sync.
generate_species_embeddingB
Generate or refresh the 1024-dimensional semantic embedding for a species.
Inputs: id (required), sync.
get_biomeA
Retrieve details of a single biome including its member species.
Inputs: id (required), include_species.
get_cluster_groupA
Retrieve details of a specific archetype cluster group with all member species or organisms.
Inputs: id (required), include_members.
get_cluster_reportB
Retrieve complete scholarly biological report content, progress percentage, markdown monograph, and intermediate summaries.
Inputs: id (required), include_summaries, include_sub_reports.
get_cluster_snapshotC
Retrieve details of a frozen cluster snapshot including member groups and generated synthesis reports.
Inputs: id (required), include_groups, include_members, include_reports.
get_job_statusB
Check the status, progress, and result of an ActiveJob/Sidekiq background task.
Inputs: job_id (required).
get_openapi_specA
Retrieve the raw OpenAPI 3.1 specification for the Biologist API.
Inputs: no named parameters.
get_organismA
Retrieve details of a single individual organism including parent species and biome.
Inputs: id (required), include_embedding.
get_platform_statusA
Get overall platform health, catalog entity counts, embedding coverage stats, and active LLM configuration.
Inputs: no named parameters.
get_report_sub_reportC
Retrieve a single Phase 2 batch analysis.
Inputs: id (required).
get_report_summaryC
Retrieve a single Phase 1 per-cluster scholarly summary.
Inputs: id (required).
get_settingsA
Get embedding completion metrics for Species and Organisms, active embedding/LLM parameters, and context window presets.
Inputs: no named parameters.
get_speciesB
Retrieve details of a single biological species including its biome and child organisms.
Inputs: id (required), include_embedding, include_organisms.
list_biomesB
List biomes (global ecosystems, climatic zones, and primary environmental regimes) registered in Biologist with species counts.
Inputs: q, limit, offset, include_species.
list_cluster_groupsC
List all archetype cluster groups belonging to a specific frozen snapshot.
Inputs: cluster_snapshot_id (required), limit, offset, include_members.
list_cluster_reportsC
List generated multi-phase comparative biology and ecological manifold synthesis reports.
Inputs: limit, offset, status, is_detailed, +2 more.
list_cluster_snapshotsC
List frozen archetype cluster snapshots in Biologist.
Inputs: limit, offset, target_type.
list_jobsB
List recent asynchronous background jobs (embedding calculations, LLM discoveries, synthesis reports).
Inputs: limit.
list_organismsB
List individual organisms (morphs, castes, sexual dimorphisms, life-history stages) with filtering by species, biome, themes, and embedding status.
Inputs: q, limit, theme, offset, +4 more.
list_report_sub_reportsB
List all Phase 2 intermediate batch analyses belonging to a detailed synthesis report.
Inputs: cluster_report_id (required).
list_report_summariesB
List all Phase 1 per-cluster analyses belonging to a synthesis report.
Inputs: cluster_report_id (required).
list_speciesB
List species registered in Biologist with filtering by biome, themes, embedding status, and search keywords.
Inputs: q, limit, theme, offset, +4 more.
populate_biomesB
Trigger LLM discovery to populate major global biomes and environmental regimes.
Inputs: no named parameters.
populate_biome_speciesC
Discover and populate canonical species for a specific biome via LLM generation.
Inputs: id (required), sync, count.
populate_organisms_bulkB
Trigger LLM discovery to populate individual organisms across all registered species.
Inputs: no named parameters.
populate_species_bulkB
Trigger LLM discovery to populate species across all registered biomes.
Inputs: no named parameters.
populate_species_organismsC
Discover and populate individual organisms, castes, or morphs for a specific species via LLM generation.
Inputs: id (required), sync, count.
searchC
Unified cross-catalog semantic or keyword search across species and individual organisms in the Biologist comparative biology manifold.
Inputs: q (required), mode, limit, target_type.
trigger_bulk_embeddingsC
Enqueue bulk embedding generation for all Species or Organisms.
Inputs: model_type (required), only_missing.
update_biomeC
Update an existing biome's name or description.
Inputs: id (required), name, description.
update_context_windowC
Dynamically update the active LLM context window token size.
Inputs: context_window (required).
update_organismC
Update an existing organism's attributes, species assignment, or themes.
Inputs: id (required), name, themes, species_id, +1 more.
update_speciesC
Update an existing species's attributes, biome assignment, or themes.
Inputs: id (required), name, themes, biome_id, +1 more.
upsert_biomes_batchB
Batch insert or update biomes matching case-insensitively on name.
Inputs: biomes (required).
upsert_organisms_batchB
Batch insert or update organisms scoped to a specific species matching case-insensitively on name.
Inputs: organisms (required), species_id (required).
upsert_species_batchB
Batch insert or update species scoped to a specific biome matching case-insensitively on name.
Inputs: species (required), biome_id (required).
wait_for_jobA
Poll a background job until completion or failure with configurable timeout.
Inputs: job_id (required), timeout_ms, poll_interval_ms.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
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.
Maintenance
Related MCP Connectors
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Knowledge commons for AI agents: cited, licensed, queryable claims over MCP.
Hosted MCP with 91 agent tools: X, domains, SEO, Maps, Trends, Search, YouTube, TikTok, and more.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to query and traverse spec genomes via MCP tools, providing structured access to entities, relationships, and graph data.8MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to persistently store and semantically search shared knowledge via MCP tools.2MIT
- FlicenseBqualityBmaintenanceEnables AI agents to query an air-gapped enterprise knowledge vault via seven MCP tools for deterministic and hybrid retrieval, entity graph traversal, context compression, archive inspection, onboarding scans, and node status.7-
- AlicenseNot gradedqualityCmaintenanceEnables agents to run hybrid retrieval, build token-budgeted attributed context packs, answer questions with citation and groundedness-gated release, explore temporal graph entities, evaluate claim support, and ingest screened, embedded documents through typed MCP tools.Apache 2.0