// SCAN REPORT

Threads MCP Server

28 tools. 8 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 29 Jun 2026

8 can modify or destroy data

20 read-only

28 tools total

Community server · catalogue entry verified 29/06/2026

How to control Threads MCP Server ↓

TOOL MAP

What Threads MCP Server exposes to your agents

Read (20) Write / Execute (7) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Threads MCP Server tools

Destructive · High delete_thread This tool permanently removes user-created content from Threads. Write · Medium create_and_publish_thread This tool creates and publishes new content on the Threads platform, modifying the platform's data state. Write · Medium create_thread_container This tool creates new media container objects within Threads, which is a Write operation—data is created and can be subsequently modified or removed. Write · Medium manage_pending_reply This tool performs a write operation by changing the moderation state of content.

8 of Threads MCP Server's 28 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Threads MCP Server

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

Deny destructive operations

{
  "delete_thread": {
    "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

{
  "create_and_publish_thread": {
    "limits": [
      {
        "counter": "create_and_publish_thread_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "exchange_code_for_token": {
    "limits": [
      {
        "counter": "exchange_code_for_token_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 Threads MCP Server — 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 THREADS →

Instant setup, no code required.

FULL CATALOGUE

All 28 Threads MCP Server tools

DESTRUCTIVE 1 tools

Destructive delete_thread Delete a Threads post owned by the authenticated user.

WRITE 7 tools

Write create_and_publish_thread Create a Threads container and then publish it, returning both IDs. Write create_thread_container Create a Threads media container using only officially documented publish parameters. Write manage_pending_reply Approve or ignore a pending Threads reply. Write manage_reply Hide or unhide a top-level reply using the official manage_reply endpoint. Write publish_thread Publish a previously created Threads media container. Write refresh_access_token Refresh an unexpired long-lived Threads user access token. Write repost_thread Create a repost container for a published Threads post and publish it immediately.

READ 20 tools

Read exchange_code_for_token Exchange a Threads authorization code for a short-lived user access token. Read get_app_access_token Get a Threads app access token using client credentials. Read get_location Retrieve a Threads location object by ID. Read get_long_lived_access_token Exchange a short-lived Threads user access token for a long-lived token. Read get_me Return the authenticated Threads profile. Read get_mentions Return Threads posts in which the authenticated user is mentioned. Read get_oembed Retrieve oEmbed metadata for a Threads post URL. Read get_pending_replies Return pending or ignored replies for a Threads post. Read get_profile Look up a public Threads profile by exact username. Read get_profile_threads Return a paginated list of public posts for an exact Threads username. Read get_publishing_limit Return the current Threads publishing quota information for the authenticated account. Read get_replies Return the top-level replies for a Threads post. Read get_thread Return a single Threads post by ID. Read get_thread_conversation Return a flattened paginated conversation for a Threads post, including nested replies. Read get_thread_insights Return official Threads post insights for a specific thread ID. Read get_threads Return a paginated list of Threads posts for a user. Defaults to the authenticated user. Read get_user_insights Return official Threads account insights for the authenticated user or an explicit user ID. Read search_locations Search Threads locations using the official location_search endpoint. Read search_threads Search public Threads posts by keyword using the official keyword_search endpoint. Read validate_setup Validate the Threads token, account access, and infer supported scope families using safe endpoint probes.

EXPLORE

Related servers

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

FAQ

Questions about Threads MCP Server

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

Yes. The Threads MCP Server server exposes 1 destructive tools including delete_thread. 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 Threads MCP Server? +

The Threads MCP Server server has 7 write tools including create_and_publish_thread, create_thread_container, manage_pending_reply. 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 Threads MCP Server.

How many tools does the Threads MCP Server MCP server expose? +

28 tools across 3 categories: Destructive, Read, Write. 20 are read-only. 8 can modify, create, or delete data.

How do I enforce a policy on Threads MCP Server? +

Register the Threads MCP Server 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 Threads MCP Server tool call.

Deterministic rules across all 28 Threads MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON THREADS →

Instant setup, no code required.

28 Threads MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Threads MCP Server's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →