Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.cyanheads/protein-mcp-server

NPM · PROTEIN-MCP-SERVER · SCANNED SEP 20

MCP Server for 3D protein structural data retrieval & analysis from RCSB PDB, PDBe, and UniProt.

Available components

+1 this week 76 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security81
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects @opentelemetry/auto-instrumentations-node 0.64.6, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • Dependency health was assessed across the 400 of 424 dependencies we could resolve, so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency43
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (Apache-2.0).Pass
  • Actively maintained (last published 352 days ago).Pass
  • Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability84
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 856 tokens (~107/item across 8 items; 6 tools + 2 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management80
  • Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Install

How do I install the io.github.cyanheads/protein-mcp-server server?

io.github.cyanheads/protein-mcp-server runs locally as an npm package, launched with npx -y protein-mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · protein-mcp-server

# add to Claude Code
claude mcp add cyanheads-protein-mcp-server -- npx -y protein-mcp-server
// .cursor/mcp.json
{
  "mcpServers": {
    "cyanheads-protein-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "protein-mcp-server"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "cyanheads-protein-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "protein-mcp-server"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add cyanheads-protein-mcp-server -- npx -y protein-mcp-server
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cyanheads-protein-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "protein-mcp-server"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add cyanheads-protein-mcp-server --command npx --arg -y --arg protein-mcp-server
# ~/.hermes/config.yaml
mcp_servers:
  cyanheads-protein-mcp-server:
    command: "npx"
    args: ["-y", "protein-mcp-server"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "cyanheads-protein-mcp-server": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "protein-mcp-server"
      ]
    }
  }
}
# add to Vellum
assistant mcp add cyanheads-protein-mcp-server -t stdio -c npx -a -y protein-mcp-server
// mcp.json
{
  "mcpServers": {
    "cyanheads-protein-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "protein-mcp-server"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 0
    • Security disclosure: pass → unverified functional
  • 19 Sept 26 −3
    • Stability: pass → 0.77 functional
  • 18 Sept 26 0
    • Stability: 0.97 → pass security
  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 +2
    • Schema quality: fail → pass functional
    • Schema quality: excellent → good functional
  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 −2
    • Stability: pass → 0.80 functional
  • 11 Sept 26 0
    • Stability: 0.97 → pass security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed npm/protein-mcp-server@1.0.3

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 6 findings
ID CVE Severity Vector Fix available
GHSA-q7rr-3cgh-j5r3 CVE-2026-44902 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
GHSA-8988-4f7v-96qf CVE-2026-54285 medium CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L yes
GHSA-45rx-2jwx-cxfr CVE-2026-59892 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
GHSA-w5hq-g745-h8pq CVE-2026-41907 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:N yes
GHSA-9965-vmph-33xx CVE-2025-56200 medium CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N yes
GHSA-vghf-hv5q-vc2g CVE-2025-12758 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 400 packages
Packages resolved 400
Deprecated 2
Stale 97
No linked repository 1
Tree resolution Partial

The dependency tree was only partially resolved, so these counts may be incomplete.

Background: SBOMs and build attestations, explained →

MCP tools · 6 exposed · ~827 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
protein_analyze_collection ~106

Perform statistical analysis of protein structure database by fold classification, function, organism, or experimental method. Useful for understanding structural biology trends and dataset composition.

NameTypeReqDescription
analysisTypestringyesType of analysis: fold (structural classification), function, organism, or method.
filtersobjectFilters to narrow analysis scope.
groupBystringSecondary grouping dimension (e.g., year for trends).
limitintegerNumber of top categories to return.
NameTypeReqDescription
analysisTypestringyesThe type of analysis that was performed.
statisticsarrayyesAn array of statistical results for the top categories.
totalStructuresnumberyesTotal number of structures matching the query.
trendsarrayOptional array of trend data, present if `groupBy` was used.

No examples provided.

protein_compare_structures ~112

Compare multiple protein structures using structural alignment. Calculate RMSD, TM-score, and identify flexible/rigid regions. Useful for analyzing conformational changes and structural similarities.

NameTypeReqDescription
alignmentMethodstringAlignment algorithm to use.
chainSelectionsarraySpecific chain selections (default: auto-select first chain).
includeVisualizationbooleanInclude PyMOL/ChimeraX visualization script.
pdbIdsarrayyesArray of PDB IDs to compare (2-10 structures).
NameTypeReqDescription
alignmentobjectyesOverall alignment statistics.
conformationalAnalysisobjectAnalysis of flexible and rigid structural regions.
pairwiseComparisonsarrayyesPairwise comparison results for all structure pairs.
visualizationstringVisualization script.

No examples provided.

protein_find_similar ~127

Find proteins similar to a query by sequence (BLAST) or structure (DALI, FATCAT). Use for homology searches, fold recognition, and evolutionary analysis.

NameTypeReqDescription
chainIdstringSpecific chain ID for structural similarity (default: auto-select first chain "A").
limitintegerMaximum number of results.
queryobjectyesQuery: PDB ID, FASTA sequence, or structure data.
similarityTypestringyesType of similarity search: sequence or structure.
thresholdobjectSimilarity thresholds for filtering results.
NameTypeReqDescription
queryobjectyesInformation about the search query.
resultsarrayyesArray of similar structures found.
similarityTypestringyesType of similarity search performed.
totalCountnumberyesTotal number of results found.

No examples provided.

protein_get_structure ~160

Retrieve complete 3D structure data for a specific PDB entry including coordinates, experimental metadata, and annotations. Use this after searching to get detailed structural information.

NameTypeReqDescription
formatstringStructure file format: mmcif (modern, recommended), bcif (binary, efficient), pdb (legacy), pdbml (XML), or json (metadata only).
includeAnnotationsbooleanInclude functional annotations and citations.
includeCoordinatesbooleanInclude 3D coordinate data (disable for metadata-only queries).
includeExperimentalDatabooleanInclude experimental metadata (resolution, R-factors, unit cell).
pdbIdstringyes4-character PDB identifier (e.g., "1ABC", "2GBP").
NameTypeReqDescription
annotationsobjectyesFunctional annotations and literature references.
experimentalobjectyesExperimental metadata.
pdbIdstringyes4-character PDB identifier.
structureobjectyesStructure coordinate and topology data.
titlestringyesStructure title/description.

No examples provided.

protein_search_structures ~210

Search protein structures from the Protein Data Bank by name, organism, experimental method, or resolution. Returns a paginated list of matching structures with metadata. Use this to discover proteins of interest before fetching detailed structure data.

NameTypeReqDescription
experimentalMethodstringFilter by experimental method used to determine the structure.
limitintegerMaximum number of results to return (1-100, default 25).
maxResolutionnumberMaximum resolution in Angstroms (e.g., 2.0 for high-resolution structures).
minResolutionnumberMinimum resolution in Angstroms.
offsetintegerOffset for pagination (default 0).
organismstringFilter by source organism scientific name (e.g., "Homo sapiens", "Escherichia coli").
querystringyesSearch query for protein name, PDB ID, keyword, or description (e.g., "kinase", "hemoglobin", "1ABC").
NameTypeReqDescription
hasMorebooleanyesWhether more results are available for pagination.
resultsarrayyesArray of matching protein structures.
totalCountintegeryesTotal number of matching structures.

No examples provided.

protein_track_ligands ~112

Find protein structures containing specific ligands, cofactors, drugs, or binding partners. Includes binding site details for drug discovery and molecular docking.

NameTypeReqDescription
filtersobjectAdditional filters for protein selection.
includeBindingSitebooleanInclude binding site residue details.
ligandQueryobjectyesLigand query: name (e.g., "ATP"), chemical ID, SMILES, or InChI.
limitintegerMaximum number of results to return (1-100).
NameTypeReqDescription
ligandobjectyesLigand identification and properties.
structuresarrayyesProtein structures containing the ligand.
totalCountnumberyesTotal number of structures containing the ligand.

No examples provided.

Common questions

What is the io.github.cyanheads/protein-mcp-server server?

io.github.cyanheads/protein-mcp-server is listed in the public MCP registry as io.github.cyanheads/protein-mcp-server. MCP Server for 3D protein structural data retrieval & analysis from RCSB PDB, PDBe, and UniProt. This page covers its npm package (protein-mcp-server).

Is the io.github.cyanheads/protein-mcp-server server safe to use?

io.github.cyanheads/protein-mcp-server scores 76 out of 100 on VerifyMCP. We recorded 6 known advisories against it as of 20 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.cyanheads/protein-mcp-server server expose?

io.github.cyanheads/protein-mcp-server exposes 6 tools: protein_search_structures, protein_get_structure, protein_compare_structures, protein_find_similar, protein_track_ligands, protein_analyze_collection. Their descriptions and schemas cost roughly 827 tokens of context every time the server is loaded.

Is the io.github.cyanheads/protein-mcp-server server still maintained?

io.github.cyanheads/protein-mcp-server is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.cyanheads/protein-mcp-server server under?

io.github.cyanheads/protein-mcp-server declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.