// SCAN REPORT

Keshro MCP

25 tools. 17 can modify or destroy data without limits.

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

Last updated: 3 Jul 2026

17 can modify or destroy data

8 read-only

25 tools total

Community server · catalogue entry verified 03/07/2026

How to control Keshro MCP ↓

TOOL MAP

What Keshro MCP exposes to your agents

Read (8) Write / Execute (17) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Keshro MCP tools

Execute · High start_task Despite the empty description, the name 'start_task' in the context of a high-stakes engineering execution layer suggests the tool initiates execution or triggers a task. Write · Medium add_task The tool creates or adds new tasks to a plan or project, which is reversible data creation (Write category). Write · Medium add_task_artifact The tool appears to create or attach artifacts to tasks (reversible data modification), placing it in the Write category. Write · Medium append_replan_note The tool appears to modify planning notes/metadata within a project management system.

17 of Keshro MCP's 25 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Keshro MCP

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

Rate limit write operations

{
  "add_task": {
    "limits": [
      {
        "counter": "add_task_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_history": {
    "limits": [
      {
        "counter": "get_history_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 Keshro MCP — 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 KESHRO →

Instant setup, no code required.

FULL CATALOGUE

All 25 Keshro MCP tools

EXECUTE 1 tools

Execute start_task start_task

WRITE 16 tools

Write add_task add_task Write add_task_artifact add_task_artifact Write append_replan_note append_replan_note Write append_task_note append_task_note Write block_task block_task Write complete_task complete_task Write create_plan create_plan Write edit_task edit_task Write export_project export_project Write generate_plan generate_plan Write next_task next_task Write push_to_tracker push_to_tracker Write record_decision record_decision Write sync_pull sync_pull Write unblock_task unblock_task Write update_plan update_plan

READ 8 tools

Read get_history get_history Read get_plan get_plan Read get_project get_project Read list_plans list_plans Read list_projects list_projects Read list_templates list_templates Read plan_status plan_status Read preview_plan preview_plan

EXPLORE

Related servers

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

FAQ

Questions about Keshro MCP

How do I prevent bulk modifications through Keshro MCP? +

The Keshro MCP server has 16 write tools including add_task, add_task_artifact, append_replan_note. 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 Keshro MCP.

How many tools does the Keshro MCP server expose? +

25 tools across 3 categories: Execute, Read, Write. 8 are read-only. 17 can modify, create, or delete data.

How do I enforce a policy on Keshro MCP? +

Register the Keshro 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 Keshro MCP tool call.

Deterministic rules across all 25 Keshro MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON KESHRO →

Instant setup, no code required.

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