create_project
[MAINTENANCE] Create a new Meridian project. Persistent-state disclosure: on hosted Meridian, supplied text and project/session metadata are sent to and stored in Meridian's service; self-hosted deployments keep them in the configured local SQLite/Postgres database. This data is visible in the da...
This record as markdown: /tools/io-github-ajc3xc-meridian/create-project.md
What create_project does on Meridian
AI agents use create_project 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 | |
execution_mode | string | — | Executor posture for sessions on this project. 'autonomous' (default) claims and runs sprint items immediately without asking; 'interactive' asks for direction |
parent_project_id | string | — | Optional parent project id — makes this a subproject that inherits the parent's north_star when it has none of its own. Subprojects are one level deep: the pare |
Parameters from the server's own tool schema.
Why create_project is rated Medium
This tool creates new projects and persists metadata in a database (SQLite/Postgres). While the action is reversible (the description mentions 'delete the project' as a documented control), it is fundamentally a Write operation—it creates and modifies persistent state.
From the tool's definition Tool description explicitly states 'Create a new Meridian project' and 'text and project/session metadata are sent to and stored in Meridian's service'. This is data creation and persistent modification.
Attacks that exploit this kind of access
The rule that runs create_project 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_project, this is the rule to start with:
create_project 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Meridian, apply this rule, and every create_project call is checked against it from then on.
Questions about create_project
[MAINTENANCE] Create a new Meridian project. Persistent-state disclosure: on hosted Meridian, supplied text and project/session metadata are sent to and stored in Meridian's service; self-hosted deployments keep them in the configured local SQLite/Postgres database. This data is visible in the dashboard/API and later project context or handoffs. Delete individual tasks, notes, or decisions where supported, or delete the project/account 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.
create_project accepts 3 parameters: name, execution_mode, parent_project_id. Required: name. The full parameter table on this page comes from the server's own tool schema.
Register the Meridian MCP server in PolicyLayer and add a rule for create_project: 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.
create_project is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_project 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.
Set action: deny in the PolicyLayer policy for create_project. 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.
create_project 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.
More on Meridian, and thousands of servers like it.
This server
Across the catalogue