Skip to main content
Glama
brianellin

Bluesky MCP Server

by brianellin

follow-user

Enables AI assistants to follow a specific user on Bluesky by providing the user's handle. Part of the Bluesky MCP Server for managing social interactions on the ATProtocol.

Instructions

Follow a user on Bluesky

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
handleYesThe handle of the user to follow

Implementation Reference

  • The handler function that implements the 'follow-user' tool. It resolves the provided handle to a DID using agent.resolveHandle, then calls agent.follow(did) to perform the follow action, with proper error handling.
      if (!agent) {
        return mcpErrorResponse("Not logged in. Please check your environment variables.");
      }
    
      try {
        // Resolve the handle to a DID
        const resolveResponse = await agent.resolveHandle({ handle: cleanHandle(handle) });
        
        if (!resolveResponse.success) {
          return mcpErrorResponse(`Failed to resolve handle: ${handle}`);
        }
        
        const did = resolveResponse.data.did;
        await agent.follow(did);
        
        return mcpSuccessResponse(`Successfully followed @${handle}`);
      } catch (error) {
        return mcpErrorResponse(`Error following user: ${error instanceof Error ? error.message : String(error)}`);
      }
    }
  • Input schema using Zod: requires a 'handle' parameter which is a string describing the user's handle (e.g., alice.bsky.social).
      handle: z.string().describe("The handle of the user to follow"),
    },
    async ({ handle }) => {
  • src/index.ts:681-707 (registration)
    The MCP server.tool registration for the 'follow-user' tool, including name, description, input schema, and handler reference.
      "follow-user",
      "Follow a user on Bluesky",
      {
        handle: z.string().describe("The handle of the user to follow"),
      },
      async ({ handle }) => {
        if (!agent) {
          return mcpErrorResponse("Not logged in. Please check your environment variables.");
        }
    
        try {
          // Resolve the handle to a DID
          const resolveResponse = await agent.resolveHandle({ handle: cleanHandle(handle) });
          
          if (!resolveResponse.success) {
            return mcpErrorResponse(`Failed to resolve handle: ${handle}`);
          }
          
          const did = resolveResponse.data.did;
          await agent.follow(did);
          
          return mcpSuccessResponse(`Successfully followed @${handle}`);
        } catch (error) {
          return mcpErrorResponse(`Error following user: ${error instanceof Error ? error.message : String(error)}`);
        }
      }
    );

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.5/5.0
Behavior2/5

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

No annotations are provided, so the description carries full responsibility for disclosing behavioral traits. It only states the action ('Follow a user on Bluesky') and does not mention idempotency, effects on existing relationships, return values, or failure modes. This is a significant gap for a mutation tool.

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

Conciseness5/5

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

The description is a single, concise sentence that is front-loaded with the action and resource. No unnecessary words or details, earning a top score for efficiency.

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

Completeness3/5

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

The tool is simple with one parameter and no output schema, so the description is minimally adequate. However, without any annotation or output information, a truly complete description would mention what happens after following (e.g., returns nothing, or returns the follow record). It meets the minimum viability bar.

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 coverage for the parameter is 100%: the 'handle' property is clearly described as 'The handle of the user to follow'. The description adds no extra semantic value beyond the schema, so the baseline of 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 uses a specific verb ('Follow') and resource ('a user on Bluesky'), making the tool's purpose immediately clear. It also distinguishes from the sibling 'unfollow-user' tool by naming the action directly.

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

Usage Guidelines3/5

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

The description implies usage (call this to follow a user), and the sibling 'unfollow-user' provides a natural contrast, but there is no explicit statement about when to use vs. alternatives or any prerequisites. It is adequate for such a simple tool but lacks explicit guidance.

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

Related Tools