Atlas / MCP servers / augmented-nature / AlphaFold

AlphaFoldSAFE

mcp/augmented-nature/alphafold

A comprehensive Model Context Protocol (MCP) server that provides access to the AlphaFold Protein Structure Database through a rich set of tools and resources for protein structure prediction analysis.

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
19 19r · 0w · 0d
Transport
stdio
License
NOASSERTION
Stars
35
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

A comprehensive Model Context Protocol (MCP) server that provides access to the AlphaFold Protein Structure Database through a rich set of tools and resources for protein structure prediction analysis.

Overview

This MCP server enables seamless integration with AlphaFold's vast collection of protein structure predictions, offering tools for structure retrieval, confidence analysis, batch processing, and visualization preparation. Perfect for researchers, bioinformaticians, and structural biologists working with predicted protein structures.

Features

🧬 Core Structure Tools

  • Structure Retrieval: Get AlphaFold predictions by UniProt ID
  • Multi-format Downloads: Support for PDB, CIF, BCIF, and JSON formats
  • Availability Checking: Verify if predictions exist for specific proteins

🔍 Search & Discovery

  • Structure Search: Find proteins by name, gene, or organism
  • Organism Browsing: List all available structures for specific species
  • Coverage Statistics: Get comprehensive organism-level statistics

📊 Confidence & Quality Analysis

  • Per-residue Confidence: Detailed confidence scores for each amino acid
  • Region Analysis: Identify high/low confidence structural regions
  • Quality Validation: Assess overall prediction reliability

⚡ Batch Processing

  • Bulk Retrieval: Process multiple proteins simultaneously
  • Batch Downloads: Efficient multi-structure downloads
  • Parallel Analysis: Confidence analysis for protein sets

🔬 Comparative Analysis

  • Structure Comparison: Side-by-side analysis of multiple proteins
  • Similarity Search: Find structurally related proteins
  • Coverage Comparison: Analyze prediction completeness

🎨 Visualization Integration

  • PyMOL Scripts: Ready-to-use visualization scripts
  • ChimeraX Integration: Confidence-colored structure viewing
  • Custom Export Formats: F
Read from source at commit 72c00265efb6OBSERVED · 2026-10-08
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add alphafold-server -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "alphafold-server": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
03

Exposed tools (19)

19 read · 0 write · 0 destructive.

ToolRiskDescription
analyze_confidence_regionsreadAnalyze confidence score distribution and identify high/low confidence regions
batch_confidence_analysisreadAnalyze confidence scores for multiple proteins
batch_downloadreadDownload multiple structure files
batch_structure_inforeadGet structure information for multiple proteins simultaneously
check_availabilityreadCheck if AlphaFold structure prediction is available for a UniProt ID
compare_structuresreadCompare multiple AlphaFold structures for analysis
download_structurereadDownload AlphaFold structure file in specified format
export_for_chimeraxreadExport structure data formatted for ChimeraX visualization
export_for_pymolreadExport structure data formatted for PyMOL visualization
find_similar_structuresreadFind AlphaFold structures similar to a given protein
get_api_statusreadCheck AlphaFold API status and database statistics
get_confidence_scoresreadGet per-residue confidence scores for a structure prediction
get_coverage_inforeadGet information about sequence coverage in the AlphaFold prediction
get_organism_statsreadGet statistics about AlphaFold coverage for an organism
get_prediction_metadatareadGet metadata about the prediction including version, date, and quality metrics
get_structurereadGet AlphaFold structure prediction for a specific UniProt ID
list_by_organismreadList all available structures for a specific organism
search_structuresreadSearch for available AlphaFold structures by protein name or gene
validate_structure_qualityreadValidate and assess the overall quality of an AlphaFold prediction
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (5 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (1)

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, axios, @types/node, typescript
Why it matters. 4 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 72c00265efb6full audit observations/trust-audit/mcp-server/augmented-nature__alphafold.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-0872c00265efb6SAFEB89first audit
06

Questions

What is the AlphaFold MCP server?

A comprehensive Model Context Protocol (MCP) server that provides access to the AlphaFold Protein Structure Database through a rich set of tools and resources for protein structure prediction analysis.

What tools does AlphaFold expose?

19 in total: 19 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is AlphaFold safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does AlphaFold need?

No credential environment variables were found in its source, so it appears to need none.

How does AlphaFold run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as alphafold-server at 1.0.0.

How current is this page?

The grade is for one exact copy of the source (72c00265efb6), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement