Manufact

Back to submission

seqera-mcp-server

mcp.seqera.io/mcp

Protocol: MCP 2025-03-26
Server version: 1.7.0
Supports: Tools
Resources
Prompts

Overall score

Last reviewed at Oct 15, 2026, 06:01:35 UTC

Server metadata

4 of 8 fields50/1005 / 10 pts

Identity, discovery, and usage metadata advertised during the MCP handshake.

Stable server name

seqera-mcp-server

10/10Source

Human-readable title

Add a human-readable title for clients and directories.

0/10Source

Useful description

Describe what the server helps an agent do.

0/20Source

Server version

Version 1.7.0

10/10Source

Public website

Link to a public website or documentation page.

0/10Source

Scalable or high-resolution icon

Advertise a vector or at least 128px server icon.

0/10Source

Server instructions

Usage instructions provided for agents.

20/20Source

Declared capabilities

Supports Tools, Resources, Prompts.

10/10Source

Server instructions

This is the Seqera MCP Server that provides AI assistants with access to containerized workflow tools and the Seqera Platform ecosystem. 🔬 **Seqera Platform Integration** • Complete workflow management: launch, monitor, and analyze Nextflow pipelines on Seqera • Complete Platform API access: 74+ tools covering all Seqera Platform operations including workflows, organizations, compute environments, datasets • You can pull the latest runs that happened on Seqera with this toolset • To create a new pipeline on Seqera you need to make sure that you have the proper compute environments associated with it • Compute environment configuration (AWS, Azure, GCP, HPC clusters) • Dataset management and sharing. These are csvs that just show where the data is, not the data itself. • Access control and team collaboration 🧬 **Wave Container Service** • Create containerized environments with conda packages, pip packages, or custom Docker images • Generate container build requests with automatic dependency resolution • Support for bioinformatics tools from conda-forge and bioconda channels • Perfect for creating containers for scientific computing and workflow execution for Nextflow pipelines • If you get errors associated with the environment in your workflow, you can use these tools to create a container with the proper environment • Perfect for scientific computing and workflow execution 🧩 **nf-core Bioinformatics Modules** • Search 1000+ pre-built, standardized Nextflow modules using natural language queries • Get comprehensive execution information including input/output schemas, command templates, and configuration examples • Modules cover common bioinformatics tasks: alignment, variant calling, quality control, assembly, annotation • Each module wraps popular tools (FastQC, BWA, samtools, etc.) with standardized interfaces • Containerized modules with automatic dependency management • WORKFLOW: 1) Use 'search_nfcore_module' to find re

Protocol

Pass100/10020 / 20 pts

Connection, authentication, and protocol compatibility.

Tools list returns results

7 tool(s) returned

Source

MCP negotiation succeeds (v1/v2)

MCP legacy negotiation succeeded in 394ms

Source

Resources list responds

0 resource(s) returned

Source

Server declares tools capability

Server declares tools capability in initialize response

Source

Tools

Issues73/10021.9 / 30 pts

Tool definitions, annotations, and client compatibility.

All tools have descriptions

All tools have non-empty descriptions

Skills over MCP resources are readable

Server does not advertise the Skills over MCP extension

Claude Code metadata fits its 2 KB fields

1 metadata field(s) exceed Claude Code's 2 KB truncation point

How to fix: Keep each tool description and the server instructions field at or below 2 KB, and put critical guidance first.

warningclaude-code

Source

All tools have OpenAI behavior hints

21 behavior annotation issue(s) found

How to fix: On each tool, declare annotations.readOnlyHint, annotations.destructiveHint, and annotations.openWorldHint as booleans. The policy review separately assesses whether their values match the tool's actual behavior.

errorChatGPT

Source

Claude tools declare applicable behavior hints

7 Claude behavior annotation issue(s) found

How to fix: For Claude directory submission, declare the applicable annotations.readOnlyHint or annotations.destructiveHint value as a boolean on every tool.

errorClaude.ai

Source

All tools have a display title

7 tool(s) missing a display title: search_seqera_api, call_seqera_api, search_nfcore_module, describe_nfcore_module, nfcore_suggest_analysis, search_data_tool, call_data_tool

How to fix: Set the top-level tool.title to a short human-readable label (for example, "Search catalog"). Claude directory submission requires tool titles; annotations.title remains accepted only as a legacy fallback.

errorClaude.ai

Source

Claude tool names are within 64 characters

All tool names are within Claude's 64-character limit

Source

Cursor tool-name budget advisory

No tool name independently exhausts Cursor's observed 60-character combined budget

Observed behavior

Tool names use valid characters

All tool names use valid characters

Source

Tool names follow the MCP 1–128 character range

All tool names follow the MCP recommended length

Source

ChatGPT tool names are unique

All tool names are unique

Source

Tool names follow MCP uniqueness guidance

All tool names are unique

Source

Tool input schemas have a valid object structure

All tool input schemas have a valid object structure

Source

Tool input header annotations are valid

All x-mcp-header annotations satisfy Streamable HTTP requirements

Source

OpenAI file parameters use valid schemas

All declared OpenAI file parameters use reviewer-valid schemas

Source

Declared output schemas have a valid basic structure

0 declared output schema(s) pass basic structural validation; schemas may describe any JSON value, including arrays

Source

Tool text has no hidden control characters

No invisible or control characters found in tool-facing text

Source

MCP Apps

Not applicable-Optional

App resources, metadata, and rendering requirements.

View resource envelope is valid

No view resources found — view checks skipped

Tool invocation metadata present

No view resources found — view checks skipped

Source

All discovered view resources were inspected

No view resources found — view checks skipped

Source

Tool-linked resource URI is readable

No view resources found — view checks skipped

Source

View resources declare a domain

No view resources found — view checks skipped

Source

View resource metadata complete

No view resources found — view checks skipped

Source

Tool visibility metadata is valid

No view resources found — view checks skipped

Source

Declared domains respond

No view resources found — view checks skipped

CSP metadata covers literal external origins

No view resources found — view checks skipped

Source

Tool documentation quality

7 tools reviewed57/10022.8 / 40 pts

How clearly each tool’s title, description, input and output schemas, and behavior annotations guide an agent.

search_seqera_apiTitles 39Descriptions 90Inputs 75Annotations 0Outputs 054/100

Title39/100

Not provided

Add a human-readable title so users do not have to interpret the tool identifier.

Description90/100

WHEN TO USE: When you need to help users accomplish tasks in the Seqera ecosystem (workflows, containers, packages) but don't know which specific API to call. WHAT IT DOES: Takes a natural language description of the user's goal and returns ranked suggestions of the most relevant Seqera APIs with complete parameter details and usage examples. USE THIS FIRST before call_seqera_api. AGENT GUIDANCE: Pass the user's intent directly - don't pre-process or guess API names yourself.

The description explains the capability, when to use it, and what to expect.

Inputs75/100

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

query

AGENT INSTRUCTION: Pass the user's request as-is, using their exact words when possible. Examples: 'show my running workflows', 'create a Python environment', 'find bioinformatics tools', 'set up cloud computing', 'help me analyze genomic data', 'I need to run a pipeline'. The more natural and specific, the better the API suggestions will be.

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

limit

AGENT INSTRUCTION: Request 3-5 suggestions for most cases, up to 10 for complex or exploratory requests. More suggestions = more options but longer response.

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

service_filter

AGENT INSTRUCTION: Only use this filter if the user specifically mentions: 'platform' (workflows, pipelines, data analysis), 'wave' (containers, environments), 'seqerahub' (software packages), 'data' (reference genomes, sequencing data). Leave empty for general requests to get suggestions from all services.

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

Annotations0/100

Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.

Not declared

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "search_seqera_api",
  "description": "WHEN TO USE: When you need to help users accomplish tasks in the Seqera ecosystem (workflows, containers, packages) but don't know which specific API to call. WHAT IT DOES: Takes a natural language description of the user's goal and returns ranked suggestions of the most relevant Seqera APIs with complete parameter details and usage examples. USE THIS FIRST before call_seqera_api. AGENT GUIDANCE: Pass the user's intent directly - don't pre-process or guess API names yourself.",
  "inputSchema": {
    "type": "object",
    "required": [
      "query"
    ],
    "properties": {
      "limit": {
        "type": "integer",
        "default": 5,
        "maximum": 10,
        "minimum": 1,
        "description": "AGENT INSTRUCTION: Request 3-5 suggestions for most cases, up to 10 for complex or exploratory requests. More suggestions = more options but longer response."
      },
      "query": {
        "type": "string",
        "description": "AGENT INSTRUCTION: Pass the user's request as-is, using their exact words when possible. Examples: 'show my running workflows', 'create a Python environment', 'find bioinformatics tools', 'set up cloud computing', 'help me analyze genomic data', 'I need to run a pipeline'. The more natural and specific, the better the API suggestions will be."
      },
      "service_filter": {
        "type": "array",
        "items": {
          "enum": [
            "platform",
            "wave",
            "seqerahub",
            "data"
          ],
          "type": "string"
        },
        "description": "AGENT INSTRUCTION: Only use this filter if the user specifically mentions: 'platform' (workflows, pipelines, data analysis), 'wave' (containers, environments), 'seqerahub' (software packages), 'data' (reference genomes, sequencing data). Leave empty for general requests to get suggestions from all services."
      }
    }
  }
}

call_seqera_apiTitles 41Descriptions 90Inputs 75Annotations 0Outputs 055/100

Title41/100

Not provided

Add a human-readable title so users do not have to interpret the tool identifier.

Description90/100

WHEN TO USE: After search_seqera_api returns API recommendations, use this to execute the chosen API. WHAT IT DOES: Calls the specific Seqera API (Platform, Wave, or SeqeraHub) with the provided parameters and returns the actual results. AGENT WORKFLOW: 1) Get suggestions from search_seqera_api, 2) Pick the best match, 3) Use this tool with the exact api_name and parameter schema from the suggestion. CRITICAL: Always use the exact api_name from suggestions - don't modify it. IMPORTANT: 'parameters' must match the MCP tool schema returned in the recommendation, including nested objects such as 'launch' when shown. Do NOT pass raw HTTP envelopes like {method, endpoint, body}.

Describe the returned information so the agent knows whether it will answer the request.

Inputs75/100

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

service

AGENT INSTRUCTION: Use the exact 'service' value from search_seqera_api results. Must be 'platform', 'wave', 'seqerahub', or 'data'.

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

api_name

AGENT INSTRUCTION: Copy the exact 'api_name' from search_seqera_api results (e.g., 'platform_list_workflows', 'wave_claim_container'). Do NOT modify, translate, or adapt this name - use it exactly as provided.

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

parameters

AGENT INSTRUCTION: Use the parameter structure suggested in the API recommendation. Start with the suggested parameters and adapt values based on user's specific request (e.g., change workspaceId, package names, etc.). If no parameters needed, use empty object {}.

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

Annotations0/100

Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.

Not declared

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "call_seqera_api",
  "description": "WHEN TO USE: After search_seqera_api returns API recommendations, use this to execute the chosen API. WHAT IT DOES: Calls the specific Seqera API (Platform, Wave, or SeqeraHub) with the provided parameters and returns the actual results. AGENT WORKFLOW: 1) Get suggestions from search_seqera_api, 2) Pick the best match, 3) Use this tool with the exact api_name and parameter schema from the suggestion. CRITICAL: Always use the exact api_name from suggestions - don't modify it. IMPORTANT: 'parameters' must match the MCP tool schema returned in the recommendation, including nested objects such as 'launch' when shown. Do NOT pass raw HTTP envelopes like {method, endpoint, body}.",
  "inputSchema": {
    "type": "object",
    "required": [
      "service",
      "api_name",
      "parameters"
    ],
    "properties": {
      "service": {
        "enum": [
          "platform",
          "wave",
          "seqerahub",
          "data"
        ],
        "type": "string",
        "description": "AGENT INSTRUCTION: Use the exact 'service' value from search_seqera_api results. Must be 'platform', 'wave', 'seqerahub', or 'data'."
      },
      "api_name": {
        "type": "string",
        "description": "AGENT INSTRUCTION: Copy the exact 'api_name' from search_seqera_api results (e.g., 'platform_list_workflows', 'wave_claim_container'). Do NOT modify, translate, or adapt this name - use it exactly as provided."
      },
      "parameters": {
        "type": "object",
        "description": "AGENT INSTRUCTION: Use the parameter structure suggested in the API recommendation. Start with the suggested parameters and adapt values based on user's specific request (e.g., change workspaceId, package names, etc.). If no parameters needed, use empty object {}.",
        "additionalProperties": true
      }
    }
  }
}

search_nfcore_moduleTitles 46Descriptions 82Inputs 88Annotations 0Outputs 058/100

Title46/100

Not provided

The title clearly communicates the tool’s action and subject. Keep it concise.

Description82/100

Search for nf-core bioinformatics modules using natural language queries. nf-core modules are containerized, standardized tools for common bioinformatics tasks (alignment, variant calling, quality control, assembly, annotation, etc.). Each module wraps tools like FastQC, BWA, or samtools with standardized interfaces for Nextflow execution. WORKFLOW: 1) Use this tool to find relevant modules, 2) Use describe_nfcore_module to get execution details. 3) Run it with Nextflow if required by the user.

The description explains the capability, when to use it, and what to expect.

Inputs88/100

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

query

Natural language description of the desired functionality (e.g., 'BAM file statistics', 'sequence alignment', 'variant calling')

Clear enough to supply this argument.

limit

Number of module suggestions to return (default: 5, max: 20)

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

Annotations0/100

Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.

Not declared

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "search_nfcore_module",
  "description": "Search for nf-core bioinformatics modules using natural language queries. nf-core modules are containerized, standardized tools for common bioinformatics tasks (alignment, variant calling, quality control, assembly, annotation, etc.). Each module wraps tools like FastQC, BWA, or samtools with standardized interfaces for Nextflow execution. WORKFLOW: 1) Use this tool to find relevant modules, 2) Use describe_nfcore_module to get execution details. 3) Run it with Nextflow if required by the user.",
  "inputSchema": {
    "type": "object",
    "required": [
      "query"
    ],
    "properties": {
      "limit": {
        "type": "integer",
        "default": 5,
        "maximum": 20,
        "minimum": 1,
        "description": "Number of module suggestions to return (default: 5, max: 20)"
      },
      "query": {
        "type": "string",
        "description": "Natural language description of the desired functionality (e.g., 'BAM file statistics', 'sequence alignment', 'variant calling')"
      }
    }
  }
}

describe_nfcore_moduleTitles 44Descriptions 94Inputs 75Annotations 0Outputs 057/100

Title44/100

Not provided

Add a human-readable title so users do not have to interpret the tool identifier.

Description94/100

Get comprehensive metadata and a ready-to-run Nextflow command for a specific nf-core module. CRITICAL: This tool returns ONE complete, executable Nextflow command in the 'READY_TO_RUN_COMMAND.nextflow_command' field - AI assistants should provide this exact command to users, not create custom workflows. IMPORTANT: Before running the command, the module must be installed locally using 'nf-core modules install <module_name>'. The response includes: detailed description, input/output schemas, and a production-ready execution command with Docker and Wave integration. Use this tool after finding a module with search_nfcore_module to get the exact command needed to run the module with the user's data. AI assistants: Always use the provided command exactly as-is, only help customize file paths.

The description explains the capability, when to use it, and what to expect.

Inputs75/100

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

module_name

Name of the nf-core module (e.g., 'nf-core/fastqc', 'nf-core/bwa/mem')

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

Annotations0/100

Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.

Not declared

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "describe_nfcore_module",
  "description": "Get comprehensive metadata and a ready-to-run Nextflow command for a specific nf-core module. CRITICAL: This tool returns ONE complete, executable Nextflow command in the 'READY_TO_RUN_COMMAND.nextflow_command' field - AI assistants should provide this exact command to users, not create custom workflows. IMPORTANT: Before running the command, the module must be installed locally using 'nf-core modules install <module_name>'. The response includes: detailed description, input/output schemas, and a production-ready execution command with Docker and Wave integration. Use this tool after finding a module with search_nfcore_module to get the exact command needed to run the module with the user's data. AI assistants: Always use the provided command exactly as-is, only help customize file paths.",
  "inputSchema": {
    "type": "object",
    "required": [
      "module_name"
    ],
    "properties": {
      "module_name": {
        "type": "string",
        "description": "Name of the nf-core module (e.g., 'nf-core/fastqc', 'nf-core/bwa/mem')"
      }
    }
  }
}

nfcore_suggest_analysisTitles 50Descriptions 96Inputs 75Annotations 0Outputs 059/100

Title50/100

Not provided

Add a human-readable title so users do not have to interpret the tool identifier.

Description96/100

Suggest appropriate nf-core pipeline and reference genome for analysis. Given library strategy and/or organism, returns recommendations for: PIPELINE MAPPINGS: • RNA-Seq → nf-core/rnaseq • WGS/WXS → nf-core/sarek • ATAC-Seq → nf-core/atacseq • ChIP-Seq → nf-core/chipseq • Bisulfite-Seq → nf-core/methylseq • Amplicon → nf-core/ampliseq • miRNA-Seq → nf-core/smrnaseq • Hi-C → nf-core/hic GENOME MAPPINGS (AWS iGenomes): • Homo sapiens → GRCh38 • Mus musculus → GRCm39 • Rattus norvegicus → Rnor_6.0 • Danio rerio → GRCz11 • Drosophila melanogaster → BDGP6 • Caenorhabditis elegans → WBcel235 • Saccharomyces cerevisiae → R64-1-1 • Arabidopsis thaliana → TAIR10 Returns pipeline URL (nf-co.re) and AWS iGenomes S3 path for the genome.

The description explains the capability, when to use it, and what to expect.

Inputs75/100

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

library_strategy

Library strategy (e.g., RNA-Seq, WGS, WXS, ATAC-Seq, ChIP-Seq, Bisulfite-Seq, Amplicon, miRNA-Seq, Hi-C)

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

organism

Organism scientific name (e.g., 'Homo sapiens', 'Mus musculus', 'Drosophila melanogaster')

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

Annotations0/100

Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.

Not declared

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "nfcore_suggest_analysis",
  "description": "Suggest appropriate nf-core pipeline and reference genome for analysis. Given library strategy and/or organism, returns recommendations for:\n\nPIPELINE MAPPINGS:\n• RNA-Seq → nf-core/rnaseq\n• WGS/WXS → nf-core/sarek\n• ATAC-Seq → nf-core/atacseq\n• ChIP-Seq → nf-core/chipseq\n• Bisulfite-Seq → nf-core/methylseq\n• Amplicon → nf-core/ampliseq\n• miRNA-Seq → nf-core/smrnaseq\n• Hi-C → nf-core/hic\n\nGENOME MAPPINGS (AWS iGenomes):\n• Homo sapiens → GRCh38\n• Mus musculus → GRCm39\n• Rattus norvegicus → Rnor_6.0\n• Danio rerio → GRCz11\n• Drosophila melanogaster → BDGP6\n• Caenorhabditis elegans → WBcel235\n• Saccharomyces cerevisiae → R64-1-1\n• Arabidopsis thaliana → TAIR10\n\nReturns pipeline URL (nf-co.re) and AWS iGenomes S3 path for the genome.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "organism": {
        "type": "string",
        "description": "Organism scientific name (e.g., 'Homo sapiens', 'Mus musculus', 'Drosophila melanogaster')"
      },
      "library_strategy": {
        "type": "string",
        "description": "Library strategy (e.g., RNA-Seq, WGS, WXS, ATAC-Seq, ChIP-Seq, Bisulfite-Seq, Amplicon, miRNA-Seq, Hi-C)"
      }
    }
  }
}

search_data_toolTitles 49Descriptions 89Inputs 75Annotations 0Outputs 057/100

Title49/100

Not provided

Add a human-readable title so users do not have to interpret the tool identifier.

Description89/100

WHEN TO USE: When you need to help users access reference genomes (iGenomes), sequencing data (SRA/ENA/FFQ), or scientific literature (PubMed) but don't know which specific API to call. WHAT IT DOES: Takes a natural language description of the user's data needs and returns ranked suggestions of relevant data operations with complete parameter details. USE THIS FIRST before call_data_tool. Examples: 'human reference genome GRCh38', 'RNA-Seq data for breast cancer', 'FASTQ files for SRR12345', 'detailed metadata for study SRP12345', 'GEO dataset GSE12345 download URLs', 'sequencing data from paper DOI 10.1038/nature12345', 'papers about CRISPR gene editing', 'citations for PMID 12345678'.

Describe the returned information so the agent knows whether it will answer the request.

Inputs75/100

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

query

Natural language description of data needs (e.g., 'human reference genome GRCh38', 'RNA-Seq data for breast cancer', 'mouse mm10 STAR indices', 'fetch metadata for SRR12345', 'get download URLs for GEO series GSE54321', 'explore ENCODE dataset ENCSR000AAA', 'find sequencing data from publication DOI', 'find papers about cancer immunotherapy', 'get citations for seminal CRISPR papers')

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

limit

Maximum number of suggestions to return (default: 5, max: 20)

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

Annotations0/100

Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.

Not declared

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "search_data_tool",
  "description": "WHEN TO USE: When you need to help users access reference genomes (iGenomes), sequencing data (SRA/ENA/FFQ), or scientific literature (PubMed) but don't know which specific API to call. WHAT IT DOES: Takes a natural language description of the user's data needs and returns ranked suggestions of relevant data operations with complete parameter details. USE THIS FIRST before call_data_tool. Examples: 'human reference genome GRCh38', 'RNA-Seq data for breast cancer', 'FASTQ files for SRR12345', 'detailed metadata for study SRP12345', 'GEO dataset GSE12345 download URLs', 'sequencing data from paper DOI 10.1038/nature12345', 'papers about CRISPR gene editing', 'citations for PMID 12345678'.",
  "inputSchema": {
    "type": "object",
    "required": [
      "query"
    ],
    "properties": {
      "limit": {
        "type": "integer",
        "default": 5,
        "maximum": 20,
        "minimum": 1,
        "description": "Maximum number of suggestions to return (default: 5, max: 20)"
      },
      "query": {
        "type": "string",
        "description": "Natural language description of data needs (e.g., 'human reference genome GRCh38', 'RNA-Seq data for breast cancer', 'mouse mm10 STAR indices', 'fetch metadata for SRR12345', 'get download URLs for GEO series GSE54321', 'explore ENCODE dataset ENCSR000AAA', 'find sequencing data from publication DOI', 'find papers about cancer immunotherapy', 'get citations for seminal CRISPR papers')"
      }
    }
  }
}

call_data_toolTitles 55Descriptions 98Inputs 63Annotations 0Outputs 058/100

Title55/100

Not provided

Add a human-readable title so users do not have to interpret the tool identifier.

Description98/100

WHEN TO USE: After search_data_tool returns operation recommendations, use this to execute the chosen operation. WHAT IT DOES: Calls the specific data operation (iGenomes, SRA/ENA, FFQ, or PubMed) with the provided parameters and returns actual data: S3 paths, file listings, sequencing data search results, download URLs, rich hierarchical metadata from FFQ (GEO/SRA/ENCODE/ENA/DDBJ/Biosample accessed via accessions or DOI), scientific papers, article abstracts, or citation networks. FFQ supports DOI-based lookups to retrieve sequencing datasets associated with scientific publications. AGENT WORKFLOW: 1) Get suggestions from search_data_tool, 2) Pick the best match, 3) Use this tool with the exact api_name and parameters from the suggestion.

The description explains the capability, when to use it, and what to expect.

Inputs63/100

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

api_name

AGENT INSTRUCTION: Copy the exact 'api_name' from search_data_tool results (e.g., 'igenomes_list_genomes', 'sra_search_ncbi'). Do NOT modify this name.

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

parameters

Operation-specific parameters from the suggestion. Adapt values based on user's request.

Explain the meaning of this value, not just its name.

Annotations0/100

Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.

Not declared

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "call_data_tool",
  "description": "WHEN TO USE: After search_data_tool returns operation recommendations, use this to execute the chosen operation. WHAT IT DOES: Calls the specific data operation (iGenomes, SRA/ENA, FFQ, or PubMed) with the provided parameters and returns actual data: S3 paths, file listings, sequencing data search results, download URLs, rich hierarchical metadata from FFQ (GEO/SRA/ENCODE/ENA/DDBJ/Biosample accessed via accessions or DOI), scientific papers, article abstracts, or citation networks. FFQ supports DOI-based lookups to retrieve sequencing datasets associated with scientific publications. AGENT WORKFLOW: 1) Get suggestions from search_data_tool, 2) Pick the best match, 3) Use this tool with the exact api_name and parameters from the suggestion.",
  "inputSchema": {
    "type": "object",
    "required": [
      "api_name",
      "parameters"
    ],
    "properties": {
      "api_name": {
        "type": "string",
        "description": "AGENT INSTRUCTION: Copy the exact 'api_name' from search_data_tool results (e.g., 'igenomes_list_genomes', 'sra_search_ncbi'). Do NOT modify this name."
      },
      "parameters": {
        "type": "object",
        "description": "Operation-specific parameters from the suggestion. Adapt values based on user's request.",
        "additionalProperties": true
      }
    }
  }
}

Put your MCP to the test

A few tasks worth trying with this server, chosen from its reviewed tools. These have not been run.

01Search nfcore moduleSearch for nf-core bioinformatics modules using natural language queries.
02Nfcore suggest analysisSuggest appropriate nf-core pipeline and reference genome for analysis.
03Search data toolWHEN TO USE: When you need to help users access reference genomes (iGenomes), sequencing data (SRA/ENA/FFQ), or scientific literature (PubMed) but don't know…
04Search seqera apiWHEN TO USE: When you need to help users accomplish tasks in the Seqera ecosystem (workflows, containers, packages) but don't know which specific API to call.
05Describe nfcore moduleGet comprehensive metadata and a ready-to-run Nextflow command for a specific nf-core module.

Want to run these tasks against your MCP server with us?

Test your MCP in Cloud Book a test call

Overview

Category: Developer tools

FAQ

seqera-mcp-server setup, tools, quality score, publishing readiness, and alternatives.

How do I add seqera-mcp-server to Claude, ChatGPT, or Cursor?

Add seqera-mcp-server to Claude, ChatGPT, or Cursor by connecting its remote MCP URL in each client's MCP settings. In Claude, add a custom connector. In ChatGPT, add an MCP app. In Cursor, add an MCP server under Settings. The MCP URL is https://mcp.seqera.io/mcp.

Is seqera-mcp-server MCP ready for ChatGPT and Claude?

As of October 15, 2026, seqera-mcp-server scores 78/100 on Manufact's MCP publishing checklist. The scan does not yet meet ChatGPT publishing checks and does not yet meet Claude publishing checks. Passing these checks does not guarantee marketplace approval.

How clear is seqera-mcp-server's MCP tool documentation?

As of October 15, 2026, seqera-mcp-server scores 57/100 in Manufact's review of tool titles, descriptions, input and output schemas, and behavior annotations. The review covers 7 of 7 discovered tools. The quality score measures documentation clarity; runtime behavior and marketplace readiness require separate checks.

What are the best alternatives to seqera-mcp-server?

As of October 15, 2026, alternatives to seqera-mcp-server in developer-tools on the Manufact MCP catalog include Held at the Gate, turva.dev, AgentMail, Celesto Cloud Computers, and GitCafe.

How can seqera-mcp-server improve its MCP documentation?

search_seqera_api is the lowest-scoring reviewed tool at 54/100. Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior. Open its review for feedback and a copyable fix prompt, then rerun the documentation review after updating your tool metadata.

Not your MCP?

Review any public or OAuth MCP server for protocol compatibility, tool documentation, and ChatGPT and Claude publishing readiness. No account required.

Get your MCP score

Back to leaderboard

Opening your score report…

Title39/100

Not provided

Add a human-readable title so users do not have to interpret the tool identifier.

Description90/100

The description explains the capability, when to use it, and what to expect.

Inputs75/100

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

query

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

limit

AGENT INSTRUCTION: Request 3-5 suggestions for most cases, up to 10 for complex or exploratory requests. More suggestions = more options but longer response.

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

service_filter

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

Annotations0/100

Declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint based on the tool’s actual behavior.

Not declared

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "search_seqera_api",
  "description": "WHEN TO USE: When you need to help users accomplish tasks in the Seqera ecosystem (workflows, containers, packages) but don't know which specific API to call. WHAT IT DOES: Takes a natural language description of the user's goal and returns ranked suggestions of the most relevant Seqera APIs with complete parameter details and usage examples. USE THIS FIRST before call_seqera_api. AGENT GUIDANCE: Pass the user's intent directly - don't pre-process or guess API names yourself.",
  "inputSchema": {
    "type": "object",
    "required": [
      "query"
    ],
    "properties": {
      "limit": {
        "type": "integer",
        "default": 5,
        "maximum": 10,
        "minimum": 1,
        "description": "AGENT INSTRUCTION: Request 3-5 suggestions for most cases, up to 10 for complex or exploratory requests. More suggestions = more options but longer response."
      },
      "query": {
        "type": "string",
        "description": "AGENT INSTRUCTION: Pass the user's request as-is, using their exact words when possible. Examples: 'show my running workflows', 'create a Python environment', 'find bioinformatics tools', 'set up cloud computing', 'help me analyze genomic data', 'I need to run a pipeline'. The more natural and specific, the better the API suggestions will be."
      },
      "service_filter": {
        "type": "array",
        "items": {
          "enum": [
            "platform",
            "wave",
            "seqerahub",
            "data"
          ],
          "type": "string"
        },
        "description": "AGENT INSTRUCTION: Only use this filter if the user specifically mentions: 'platform' (workflows, pipelines, data analysis), 'wave' (containers, environments), 'seqerahub' (software packages), 'data' (reference genomes, sequencing data). Leave empty for general requests to get suggestions from all services."
      }
    }
  }
}

Manufact

Server metadata

Protocol

Tools

MCP Apps

Tool documentation quality

Title39/100

Description90/100

Inputs75/100

Annotations0/100

Output schema0/100

Title41/100

Description90/100

Inputs75/100

Annotations0/100

Output schema0/100

Title46/100

Description82/100

Inputs88/100

Annotations0/100

Output schema0/100

Title44/100

Description94/100

Inputs75/100

Annotations0/100

Output schema0/100

Title50/100

Description96/100

Inputs75/100

Annotations0/100

Output schema0/100

Title49/100

Description89/100

Inputs75/100

Annotations0/100

Output schema0/100

Title55/100

Description98/100

Inputs63/100

Annotations0/100

Output schema0/100

Put your MCP to the test

Overview

Related MCP servers

FAQ

Not your MCP?

Server metadata

Protocol

Tools

MCP Apps

Tool documentation quality

Title39/100

Description90/100

Inputs75/100

Annotations0/100

Output schema0/100

Title41/100

Description90/100

Inputs75/100

Annotations0/100

Output schema0/100

Title46/100

Description82/100

Inputs88/100

Annotations0/100

Output schema0/100

Title44/100

Description94/100

Inputs75/100

Annotations0/100

Output schema0/100

Title50/100

Description96/100

Inputs75/100

Annotations0/100

Output schema0/100

Title49/100

Description89/100

Inputs75/100

Annotations0/100