// SCAN REPORT

Millimap

12 tools. 5 can modify or destroy data without limits.

5 write tools that can modify data. Rate limits recommended.

Last updated: 3 Jul 2026

5 can modify or destroy data

7 read-only

12 tools total

Community server · catalogue entry verified 03/07/2026

How to control Millimap ↓

TOOL MAP

What Millimap exposes to your agents

Read (7) Write / Execute (5) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Millimap tools

Execute · High run_clustering Running clustering is a computational operation that processes and transforms data according to algorithm parameters. Execute · High run_millimap_tool Without a description, we infer intent from context: this appears to be a dispatcher or runner for MilliMap analyses. Execute · Medium score_gene_signature Based on the name, this tool likely computes/scores a gene signature against the active dataset — a computational operation with side effects on the analysis state. Write · Medium annotate_cluster Annotation is a reversible write operation that modifies metadata associated with clusters in the active MilliMap session.

5 of Millimap's 12 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Millimap

PolicyLayer is an MCP gateway — it sits between your AI agents and Millimap, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "annotate_cluster": {
    "limits": [
      {
        "counter": "annotate_cluster_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "find_markers": {
    "limits": [
      {
        "counter": "find_markers_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Millimap — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MILLIMAP →

Instant setup, no code required.

FULL CATALOGUE

All 12 Millimap tools

EXECUTE 3 tools

Execute run_clustering run_clustering Execute run_millimap_tool run_millimap_tool Execute score_gene_signature score_gene_signature

WRITE 2 tools

Write annotate_cluster annotate_cluster Write apply_qc_filter Apply QC filters to the active dataset in MilliMap.

READ 7 tools

Read find_markers find_markers Read genes_for_cell_type Find which clusters are annotated as a given cell type, with their markers. Read get_analysis_card get_analysis_card Read get_cluster_markers Return top marker genes for a specific cluster. Read list_analysis_cards List the analysis result cards visible in MilliMap's workspace sidebar. Read list_rois List all ROIs saved in the current MilliMap session. Read search_genes Case-insensitive search across marker genes. Returns matching genes and

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Millimap

How do I prevent bulk modifications through Millimap? +

The Millimap server has 2 write tools including annotate_cluster, apply_qc_filter. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Millimap.

How many tools does the Millimap MCP server expose? +

12 tools across 3 categories: Execute, Read, Write. 7 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on Millimap? +

Register the Millimap MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Millimap tool call.

Deterministic rules across all 12 Millimap tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MILLIMAP →

Instant setup, no code required.

12 Millimap tools catalogued and risk-classified — across an index of 43,000+ MCP servers.