JSR MCP

40 tools. 18 can modify or destroy data without limits.

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

Last updated:

18 can modify or destroy data
22 read-only
40 tools total

Community server · catalogue entry verified 29/06/2026

How to control JSR MCP ↓

What JSR MCP exposes to your agents

Read (22) Write / Execute (14) Destructive / Financial (4)
Critical Risk

The most dangerous JSR MCP tools

18 of JSR MCP's 40 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control JSR MCP

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

Deny destructive operations
{
  "jsr_delete_package": {
    "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
{
  "jsr_accept_scope_invite": {
    "limits": [
      {
        "counter": "jsr_accept_scope_invite_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "jsr_get_authorization_details": {
    "limits": [
      {
        "counter": "jsr_get_authorization_details_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 JSR MCP — 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 JSR →

Instant setup, no code required.

All 40 JSR MCP tools

READ 22 tools
Read jsr_get_authorization_details Get details of an authorization. Read jsr_get_current_user Get details of the authenticated user. Read jsr_get_current_user_invites List scope invites for the authenticated user. Read jsr_get_current_user_scope_member Get details of the authenticated user Read jsr_get_current_user_scopes List scopes that the authenticated user is a member of. Read jsr_get_package Get detailed information about a specific package in the JSR registry. Read jsr_get_package_dependencies Get the dependencies of a specific package version. Read jsr_get_package_dependents Get packages that depend on a specific package. Read jsr_get_package_metadata Get package metadata from the JSR registry (versions, latest version, etc.). Read jsr_get_package_score Get the package score details for a specific package. Read jsr_get_package_version Get detailed information about a specific version of a package. Read jsr_get_publishing_task Get details of a publishing task. Read jsr_get_scope Get detailed information about a scope in the JSR registry. Read jsr_get_stats Get registry statistics including newest packages, recent updates, and featured packages. Read jsr_get_user Get details of a specific user. Read jsr_get_user_scopes List scopes that a specific user is a member of. Read jsr_list_package_versions List all available versions of a specific package. Read jsr_list_packages List all packages in the JSR registry. Read jsr_list_scope_invites List pending invites for a specific scope. Read jsr_list_scope_members List members of a specific scope. Read jsr_list_scope_packages List all packages within a specific scope. Read jsr_search_packages Search for packages in the JSR registry. Returns a list of packages matching the query.

Related servers

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

Questions about JSR MCP

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

Yes. The JSR MCP server exposes 4 destructive tools including jsr_delete_package, jsr_delete_scope, jsr_delete_scope_invite. 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 JSR MCP? +

The JSR MCP server has 12 write tools including jsr_accept_scope_invite, jsr_add_scope_member, jsr_approve_authorization. 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 JSR MCP.

How many tools does the JSR MCP server expose? +

40 tools across 3 categories: Destructive, Read, Write. 22 are read-only. 18 can modify, create, or delete data.

How do I enforce a policy on JSR MCP? +

Register the JSR 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 JSR MCP tool call.

Deterministic rules across all 40 JSR MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

40 JSR MCP 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.