create_experiment

SERVERMeridian SOURCE@meridianmcp/mcp

Medium RISK CLASS

Category Write

Parameters 51 required

Recommended Rate-limitedsee the rule below

Registry record Grade D, identity unverified Pull the record →

This record as markdown: /tools/io-github-ajc3xc-meridian/create-experiment.md

WHAT IT DOES

What create_experiment does on Meridian

AI agents use create_experiment to create or update resources in Meridian, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Meridian environment.

Parameter	Type	Required	Description
`name`	string	Yes	Bounded, non-empty experiment name.
`hypothesis`	string	—	What this experiment is testing.
`project_id`	string	—
`session_id`	string	—
`project_name`	string	—	Project name — an alternative to project_id; resolved to the id internally. project_id wins if both are given.

Parameters from the server's own tool schema.

RISK

Why create_experiment is rated Medium

An AI agent can call create_experiment faster than any human can review: one bad instruction and it creates or modifies resources in Meridian by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs create_experiment safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Meridian, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For create_experiment, this is the rule to start with:

create_experiment Rate-limited

create_experiment stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_experiment": {
      "limits": [
        {
          "counter": "create_experiment_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Meridian, apply this rule, and every create_experiment call is checked against it from then on.

FAQ

Questions about create_experiment

What does the create_experiment tool do? +

[SUPPORT] 3f6b8715 — W1-M Experiment Registry: create a named experiment (a research question; many runs belong to one). Reuses the pre-existing experiments table (4376e655) additively — config_template/created_by (an unrelated ML-style tracking interface's own columns) are left untouched. Persistent-state disclosure: on hosted Meridian, supplied text and project/session metadata -- including task log entries, pinned decisions, sprint items, notes, handoff/goal state, and HITL queue items -- are sent to and stored in Meridian's service, in an isolated per-tenant Postgres database (Neon); self-hosted deployments keep the same categories in the configured local SQLite/Postgres database. This data is visible in the dashboard and API, and may resurface in later project context or handoffs. Notes and pinned decisions can be deleted individually; task log entries and sprint items can be deleted via the dashboard/API (not exposed as an agent-facing tool); HITL queue items and handoff state have no per-record delete. Full removal of any of this data is available via project or account deletion, using the documented controls. Do not include secrets. It is categorised as a Write tool in the Meridian MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does create_experiment accept? +

create_experiment accepts 5 parameters: name, hypothesis, project_id, session_id, project_name. Required: name. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on create_experiment? +

Register the Meridian MCP server in PolicyLayer and add a rule for create_experiment: 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 Meridian. Nothing to install.

What risk level is create_experiment? +

create_experiment is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_experiment? +

Yes. Add a rate_limit block to the create_experiment 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 create_experiment completely? +

Set action: deny in the PolicyLayer policy for create_experiment. 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 create_experiment? +

create_experiment is provided by the Meridian MCP server (@meridianmcp/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Meridian, and thousands of servers like it.

This server

All 235 Meridian tools →

Across the catalogue

create_task on 0rca Dojo MCP Server →create-task on Kanban MCP Server →create_package_backup on Android Forensics ADB MCP Server →create_project on Stitch MCP Server → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →