Agentcast MCP Server

Structured-output enforcer: extract and validate JSON from messy LLM text.

Local serverstdioGo

What is the Agentcast MCP server?

Most AI and media services work still happens through a UI a human drives. Agentcast MCP server moves it into the conversation instead. Structured-output enforcer: extract and validate JSON from messy LLM text.

The short version

An MCP server that gives AI assistants the ability to enforce structured output: extract JSON from messy LLM text, gate it against a shape spec, and produce the retry feedback message when the model returns the wrong shape.

The tools it exposes

The server publishes 3 tools. What each one is for:

  • extract_json — Pull a JSON value out of messy LLM output. Tries the whole text, then a fenced json block, then the largest balanced {...} / [...] substring. Returns
  • validate_response — Validate a parsed JSON value against an agentcast shape spec. Spec maps field name to type: string, number, boolean, array, object. Suffix with ? for
  • build_retry_prompt — Given an attempt history, produce the validation-error feedback message agentcast appends to the conversation when the model returned the wrong

Getting it running

Installation goes through your MCP client rather than a global install: point it at @mukundakatta/agentcast-mcp on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

How it compares

Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Agentcast's toolset — extract_json, validate_response, build_retry_prompt — is a fair guide to whether it matches your workflow. It is maintained by MukundaKatta; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Agentcast's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
extract_jsonPull a JSON value out of messy LLM output. Tries the whole text, then a fenced json block, then the largest balanced {...} / [...] substring. Returns the parsed value plus which strategy succeeded.
validate_responseValidate a parsed JSON value against an agentcast shape spec. Spec maps field name to type: string, number, boolean, array, object. Suffix with ? for optional.
build_retry_promptGiven an attempt history, produce the validation-error feedback message agentcast appends to the conversation when the model returned the wrong shape. Codifies the "validation error as feedback" pattern for non-Node MCP

How to install the Agentcast MCP server

{
  "mcpServers": {
    "agentcast": {
      "command": "npx",
      "args": ["-y", "@mukundakatta/agentcast-mcp"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Agentcast to extract json.
  • Use Agentcast to validate response.
  • Use Agentcast to build retry prompt.

Frequently asked questions

It connects Agentcast to MCP-compatible AI assistants such as Claude and Cursor, exposing 3 tools (extract_json, validate_response, build_retry_prompt) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Agentcast directly.