Openl

41 tools. 19 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated:

19 can modify or destroy data
22 read-only
41 tools total

Community server · catalogue entry verified 01/07/2026

How to control Openl ↓

What Openl exposes to your agents

Read (22) Write / Execute (17) Destructive / Financial (2)
Critical Risk

The most dangerous Openl tools

19 of Openl's 41 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Openl

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

Deny destructive operations
{
  "delete_project_file": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "append_table": {
    "limits": [
      {
        "counter": "append_table_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "export_trace": {
    "limits": [
      {
        "counter": "export_trace_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register Openl — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON OPENL →

Instant setup, no code required.

All 41 Openl tools

READ 22 tools
Read export_trace Export trace as plain text. Returns full trace content. Use release: true to clear trace from memory after exp Read get_project Get comprehensive project information including details, modules, dependencies, and metadata. Returns full pro Read get_project_agents_md Load the AGENTS.md guidance that applies to a project as a single aggregated markdown document. Starting at th Read get_table Get detailed information about a specific table/rule. By default returns a parsed table structure with signatu Read get_test_results Get full test execution results with pagination support. Returns complete test execution summary including tes Read get_test_results_by_table Get test execution results filtered by specific table ID. Returns filtered test execution summary with only te Read get_test_results_summary Get brief test execution summary without detailed test cases. Returns aggregated statistics (execution time, t Read get_trace_node_details Get detailed trace node including parameters, context, result, and errors. Node IDs come from openl_get_trace_ Read get_trace_nodes Get trace node children (or root nodes if nodeId omitted). Use openl_start_trace first. While the trace is sti Read get_trace_parameter Get lazy-loaded parameter value. Use when a TraceParameterValue has lazy:true and parameterId set. Read list_branches List all Git branches in a repository. Returns branch names and metadata (current branch, commit info). Use th Read list_deploy_repositories List all deployment repositories in OpenL Studio. Returns repository names, their types, and status informatio Read list_deployments List all active deployments across production environments. Returns deployment names, repositories, versions, Read list_project_local_changes List local change history for a project. Returns list of workspace history items with versions, authors, times Read list_projects List all projects with optional filters (repository, status, tags). Returns project names, status (OPENED/CLOS Read list_repositories List all design repositories in OpenL Studio. Returns repository information including Read list_repository_features Get features supported by a design repository (branching, searchable, etc.). Use this to check if a repository Read list_tables List all tables/rules in a project with optional filters for type, name, and file. Returns table metadata incl Read project_status Get the post-compilation status of a project: compile state, diagnostics, pending changes, and module/test sum Read read_project_file Read any file in a project by its project-relative path — text or binary, and folder listings too. Maps to GET Read repository_project_revisions Get revision history (commit history) of a project in a design repository. Returns list of revisions with comm Read search_project_files Search a project

Related servers

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

Questions about Openl

Can an AI agent delete data through the Openl MCP server? +

Yes. The Openl server exposes 2 destructive tools including delete_project_file, delete_table. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Openl? +

The Openl server has 12 write tools including append_table, close_project, copy_project_file. 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 Openl.

How many tools does the Openl MCP server expose? +

41 tools across 4 categories: Destructive, Execute, Read, Write. 22 are read-only. 19 can modify, create, or delete data.

How do I enforce a policy on Openl? +

Register the Openl 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 Openl tool call.

Deterministic rules across all 41 Openl tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

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

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.