Mesheshq

33 tools. 13 can modify or destroy data without limits.

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

Last updated:

13 can modify or destroy data
20 read-only
33 tools total

Community server · catalogue entry verified 30/06/2026

How to control Mesheshq ↓

What Mesheshq exposes to your agents

Read (20) Write / Execute (10) Destructive / Financial (3)
Critical Risk

The most dangerous Mesheshq tools

13 of Mesheshq's 33 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Mesheshq

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

Deny destructive operations
{
  "meshes_delete_connection": {
    "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
{
  "meshes_create_connection": {
    "limits": [
      {
        "counter": "meshes_create_connection_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "meshes_emit_bulk_events": {
    "limits": [
      {
        "counter": "meshes_emit_bulk_events_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 Mesheshq — 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 MESHESHQ →

Instant setup, no code required.

All 33 Mesheshq tools

READ 20 tools
Read meshes_emit_bulk_events Emit up to 100 events in a single request. Because this MCP server uses organization-level machine credentials Read meshes_get_connection Get details of a specific connection. Does not expose raw credentials. Read meshes_get_connection_actions Get available actions for a connection (e.g., create_or_update_contact, add_to_list). Use this to discover wha Read meshes_get_connection_default_mappings Get the default field mapping for a connection. Mappings define how event payload fields map to destination fi Read meshes_get_connection_fields Get the destination field catalog for a connection. Returns field keys, types, constraints, and allowed values Read meshes_get_event Get event details including delivery status and per-rule results (rule_events). Each rule_event shows connecti Read meshes_get_event_payload Get event details including the full event payload. Useful for debugging what data was sent. Read meshes_get_rule Get details of a specific routing rule by UUID. Read meshes_get_workspace Get details of a specific workspace by UUID, including its publishable key for client-side event ingestion. Read meshes_get_workspace_connections List all connections scoped to a specific workspace. Read meshes_get_workspace_event_types List the event types configured for a workspace, including each key, label, description, and active state. Read meshes_get_workspace_events List events for a workspace with optional filters. Useful for checking delivery status, debugging, or monitori Read meshes_get_workspace_resources List the resource types configured for a workspace, including each key, label, description, and active state. Read meshes_get_workspace_rules List routing rules scoped to a specific workspace, with optional event and resource filters. Read meshes_list_connections List all connections across the organization. Connections are configured destinations (HubSpot, Salesforce, Re Read meshes_list_events List events across the organization with pagination. Read meshes_list_integrations Get metadata about all supported integration types. Returns each type Read meshes_list_rules List all routing rules across the organization. Rules bind event types to connections with action metadata. Su Read meshes_list_sessions List embedded sessions for a workspace with optional pagination, status, and resource filters. Read meshes_list_workspaces List all workspaces in the Meshes organization. Workspaces are tenant-scoped containers holding connections, r

Related servers

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

Questions about Mesheshq

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

Yes. The Mesheshq server exposes 3 destructive tools including meshes_delete_connection, meshes_delete_rule, meshes_revoke_session. 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 Mesheshq? +

The Mesheshq server has 8 write tools including meshes_create_connection, meshes_create_rule, meshes_create_session. 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 Mesheshq.

How many tools does the Mesheshq MCP server expose? +

33 tools across 3 categories: Destructive, Read, Write. 20 are read-only. 13 can modify, create, or delete data.

How do I enforce a policy on Mesheshq? +

Register the Mesheshq 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 Mesheshq tool call.

Deterministic rules across all 33 Mesheshq tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

33 Mesheshq 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.