// SCAN REPORT

SparrowDesk

32 tools. 14 can modify or destroy data without limits.

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

Last updated: 30 Jun 2026

14 can modify or destroy data

18 read-only

32 tools total

Community server · catalogue entry verified 30/06/2026

How to control SparrowDesk ↓

TOOL MAP

What SparrowDesk exposes to your agents

Read (18) Write / Execute (12) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous SparrowDesk tools

Destructive · High delete_contact The delete operation removes data that cannot be restored without external backups. Destructive · High delete_conversation Deletion of conversations is an irreversible operation that cannot be undone. Write · Medium bulk_create_contacts This tool creates new contacts (reversible data modification) in bulk. Write · Medium add_conversation_reply This tool creates or appends data (a reply or note) to a conversation without deleting or overwriting existing data, and does not execute arbitrary code or move financial resources.

14 of SparrowDesk's 32 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control SparrowDesk

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

Deny destructive operations

{
  "delete_contact": {
    "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

{
  "add_conversation_reply": {
    "limits": [
      {
        "counter": "add_conversation_reply_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_article": {
    "limits": [
      {
        "counter": "get_article_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 SparrowDesk — 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 SPARROWDESK →

Instant setup, no code required.

FULL CATALOGUE

All 32 SparrowDesk tools

DESTRUCTIVE 2 tools

Destructive delete_contact Delete a contact by ID from SparrowDesk Destructive delete_conversation Delete a conversation by ID from SparrowDesk

WRITE 12 tools

Write add_conversation_reply Add a reply or internal note to a conversation (also called a ticket) in SparrowDesk Write archive_article Archive a Knowledge Base article (hidden from the help center, not deleted) Write bulk_create_contacts Create multiple contacts in one request; returns a job_id - poll get_bulk_job_status until completed Write create_article Create a KB article (draft). Set publish true with collectionId and isPublic to publish in one step Write create_collection Create a KB collection under a help center (optionally nested under parentCollectionId) Write create_contact Create a new contact in SparrowDesk. Either email or phone must be provided. Write create_conversation Create a new conversation (also called a ticket) in SparrowDesk Write create_conversation_field Create a custom conversation field (dropdown types require field_options) Write update_article Update a KB article draft; set publish true with isPublic to publish after save Write update_contact Update an existing contact in SparrowDesk Write update_conversation Update an existing conversation (subject, status, priority, assignment, custom fields) Write update_conversation_field Update a conversation field (name, description, active flag, dropdown options, etc.)

READ 18 tools

Read get_article Get a single Knowledge Base article by ID Read get_bulk_job_status Get processing status for a bulk contact creation job returned by bulk_create_contacts Read get_collection Get a KB collection by ID with direct subcollections and paginated articles Read get_contact Retrieve a contact by ID from SparrowDesk Read get_conversation Retrieve a conversation (also called a ticket) by ID from SparrowDesk Read get_conversation_field Retrieve a single conversation field definition by ID Read get_me Retrieve current SparrowDesk account information (account id, subdomain, domain, company name, timezone, langu Read list_articles List KB articles for a help center; use published/draft/archived flags to filter lifecycle Read list_collections List KB collections for a help center (nested tree by default; use isRoot or collectionId for other views) Read list_companies List companies in the SparrowDesk account with optional filters and cursor pagination Read list_contact_fields Retrieve all contact fields from SparrowDesk Read list_contacts List contacts for the authenticated account (requires view contacts API scope) Read list_conversation_fields List conversation (ticket) custom fields Read list_conversation_replies List all replies for a conversation (also called a ticket) in SparrowDesk Read list_conversations List conversations (also called tickets) from SparrowDesk with optional filters Read list_helpcenters List Knowledge Base help centers for the account (needed for helpCenterId on articles/collections) Read list_members Retrieve a paginated list of all team members in the SparrowDesk account

EXPLORE

Related servers

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

FAQ

Questions about SparrowDesk

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

Yes. The SparrowDesk server exposes 2 destructive tools including delete_contact, delete_conversation. 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 SparrowDesk? +

The SparrowDesk server has 12 write tools including add_conversation_reply, archive_article, bulk_create_contacts. 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 SparrowDesk.

How many tools does the SparrowDesk MCP server expose? +

32 tools across 3 categories: Destructive, Read, Write. 18 are read-only. 14 can modify, create, or delete data.

How do I enforce a policy on SparrowDesk? +

Register the SparrowDesk 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 SparrowDesk tool call.

Deterministic rules across all 32 SparrowDesk tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SPARROWDESK →

Instant setup, no code required.

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