search_experiments

Search EBI Expression Atlas — ~4,500 curated gene/protein expression experiments (baseline & differential) across species, tissues, and conditions. Filter by keyword (matches description/experimental factors), species (e.g. "Homo sapiens", "Mus musculus"), and/or type ("Baseline" or "Differential...

Server Expression Atlas https://gateway.pipeworx.io/expression-atlas/mcp
Category Read
Risk class Low
Parameters 40 required

What search_experiments does on Expression Atlas

AI agents call search_experiments to retrieve information from Expression Atlas without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

ParameterTypeRequiredDescription
type string Experiment type: "Baseline" or "Differential".
limit number Max results (default 25, max 100).
query string Keyword matched (case-insensitive) against experiment description OR any experimental factor, e.g. "liver", "stress", "cancer".
species string Species substring (case-insensitive), e.g. "Homo sapiens", "Mus musculus", "Arabidopsis thaliana".

Parameters from the server's own tool schema.

Why search_experiments needs a policy

search_experiments is a pure data retrieval tool that queries a public scientific database (EBI Expression Atlas). It accepts filter parameters and returns structured metadata about experiments without creating, modifying, deleting, or executing any operations. The blast radius of misuse is minimal—an agent could only retrieve publicly available research data, which causes no harm.

From the tool's definition Tool enables querying and searching curated expression experiments with filters by keyword, species, and type; returns structured data (accession, description, species, type, assay count, factors).

Risk signalsAccepts freeform code/query input (query)

Questions about search_experiments

What does the search_experiments tool do? +

Search EBI Expression Atlas — ~4,500 curated gene/protein expression experiments (baseline & differential) across species, tissues, and conditions. Filter by keyword (matches description/experimental factors), species (e.g. "Homo sapiens", "Mus musculus"), and/or type ("Baseline" or "Differential"). Returns accession, description, species, type, assay count, and factors. Keyless. Complements UniProt/Ensembl. It is categorised as a Read tool in the Expression Atlas MCP Server, which means it retrieves data without modifying state.

What parameters does search_experiments accept? +

search_experiments accepts 4 parameters: type, limit, query, species. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on search_experiments? +

Register the Expression Atlas MCP server in PolicyLayer and add a rule for search_experiments: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Expression Atlas. Nothing to install.

What risk level is search_experiments? +

search_experiments is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit search_experiments? +

Yes. Add a rate_limit block to the search_experiments rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block search_experiments completely? +

Set action: deny in the PolicyLayer policy for search_experiments. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides search_experiments? +

search_experiments is provided by the Expression Atlas MCP server (https://gateway.pipeworx.io/expression-atlas/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.