Skip to main content
Glama
Sign In
mastodon-mcp

mastodon-mcp

by thenavidm
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Follow an account

follow_account
Idempotent

Follow any Mastodon account by username or ID. Handles locked accounts by sending a follow request, with options for notifications and showing boosts.

Instructions

Follow an account. On a locked account this sends a follow request instead.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "acct": "<acct>"
    },
    "name": "follow_account"
  }
}

Input Schema

NameRequiredDescriptionDefault
acctYes@user@instance, a bare local username, or a numeric id.
notifyNoGet a notification for every post they make.
accountNoWhich connected account to act as. Matches a full handle (alice@example.social), a bare username (alice), or an instance (example.social). Defaults to the first connected account. Call list_accounts to see them.
reblogsNoShow their boosts in your timeline. Default true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true), so the description only needs to add context beyond them. It does exactly that by disclosing that locked accounts trigger a follow request instead of a direct follow, which is a meaningful behavioral edge case not otherwise expressed in the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with no filler. The first sentence states the core action plainly, and the second front-loads an important edge case. Minor redundancy with the title exists, but nothing wasteful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple mutating tool, the description plus the rich schema parameter descriptions and annotations cover the main behavior and the key locked-account edge case. There is no output schema and no return-value detail, but that is a minor gap for a follow action and does not prevent correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the parameter descriptions already explain acct formats, notify semantics, account selection, and the reblogs default. The tool description adds no parameter-specific detail, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Follow an account') and adds an important conditional: locked accounts receive a follow request instead. The noun 'account' clearly separates it from sibling tools like follow_hashtag and from account-modifying tools such as block_account or mute_account.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use guidance, exclusion criteria, or mention of alternative tools such as follow_hashtag or answer_follow_request. The locked-account note describes behavior, not selection context, so the agent must infer usage purely from the tool name and title.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools