Structured-output enforcer: extract and validate JSON from messy LLM text.
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.
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 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. Returnsvalidate_response — Validate a parsed JSON value against an agentcast shape spec. Spec maps field name to type: string, number, boolean, array, object. Suffix with ? forbuild_retry_prompt — Given an attempt history, produce the validation-error feedback message agentcast appends to the conversation when the model returned the wrongInstallation 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.
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.
| Tool | What it does |
|---|---|
| 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 the parsed value plus which strategy succeeded. |
| 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 optional. |
| build_retry_prompt | Given 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 |
{
"mcpServers": {
"agentcast": {
"command": "npx",
"args": ["-y", "@mukundakatta/agentcast-mcp"]
}
}
}Configuration as documented by the project. Restart the client after saving.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.