bio-agents-mcp

bio-agents-mcp is a set of FastMCP-based microservices and a client for natural-language interaction with life-science data sources, specifically providing MCP servers for the Protein Data Bank (PDB) and (as described) ChEMBL, plus an LLM client and a Chainlit web UI for local use/testing.

Evaluated Apr 04, 2026 (16d ago)
Repo ↗ Ai Ml mcp fastmcp agents bioinformatics protein-data-bank chembl llm chainlit ollama python microservices
⚙ Agent Friendliness
30
/ 100
Can an agent use this?
🔒 Security
39
/ 100
Is it safe for agents?
⚡ Reliability
20
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
55
Documentation
35
Error Messages
0
Auth Simplicity
40
Rate Limits
0

🔒 Security

TLS Enforcement
60
Auth Strength
20
Scope Granularity
20
Dep. Hygiene
40
Secret Handling
60

TLS/auth details are not specified in the provided README. Docker/local configuration suggests environment variables (.env), which is a positive sign for secret handling, but there is no explicit guarantee about logging/sanitization. As an MCP tool proxy to external biological data, it may expose sensitive query context if deployed without transport/auth controls.

⚡ Reliability

Uptime/SLA
0
Version Stability
30
Breaking Changes
30
Error Recovery
20
AF Security Reliability

Best When

You want local or controlled environment experimentation/agent prototyping around PDB (and ChEMBL per the description) using FastMCP and can review module READMEs/config for operational details.

Avoid When

You cannot or will not run Docker Compose locally, or you require clearly specified auth/rate-limit/error-contract details from a single top-level API spec.

Use Cases

  • Ask questions about protein/structure information from PDB through an MCP tool interface
  • Retrieve related annotations described in the module list (e.g., UniProt annotations, PubMed annotations, structural/assembly/cluster data)
  • Build an agent workflow that uses MCP tools for life-science data retrieval
  • Local experimentation with an MCP-based architecture using a local LLM (Ollama)
  • Integrate life-science data querying into an LLM app via a provided client

Not For

  • Production deployments that require strong, documented security controls and enterprise-grade compliance (not evidenced in provided README)
  • Use cases needing a documented, stable public API contract (OpenAPI spec, typed schemas, etc.)
  • Scenarios requiring guaranteed uptime or formal SLAs (not evidenced)
  • Environments where outbound calls to external biological databases/APIs are disallowed

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

No authentication mechanism is described in the provided top-level README for the MCP servers or the client. The repository appears configured via .env, but auth specifics are not stated here.

Pricing

Free tier: No
Requires CC: No

No pricing information is applicable (open-source style repository; license is not specified in the provided metadata).

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • README does not document MCP tool schemas/arguments, pagination behavior, or retry/idempotency expectations; agents may need to handle API/transport limitations themselves.
  • Top-level README lists many functional items for the PDB module but does not show the actual tool names or response schemas; agents may require consulting module-level READMEs/config.
  • Authentication/rate-limit/error-contract details are not provided at the top level, which can lead to fragile agent behavior unless verified in module docs.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for bio-agents-mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-04-04.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered