codefmt is an MCP server published by dev.codefmt, hosted at codefmt.dev. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 3 tools, including format_code, ask_codefmt, format_json.
Format/lint JS, Python, HubL for automation platforms. Tools: format_code, format_json, ask_codefmt
721 connections through 4 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Format and lint JavaScript, Python, or HubL code for Zapier, n8n, Pipedream, Make, or HubSpot. Wraps the source in each platform's runtime shell before formatting so top-level await, bare return, and injected globals don't break the formatter. Returns formatted code plus lint diagnostics.
| Parameter | Type | Description |
|---|---|---|
| code * | string | Source code to format (≤50KB). |
| language | string | Defaults to javascript. typescript parses TypeScript on pipedream and reads as javascript elsewhere. zapier, n8n, pipedream, make, and hubspot support python; hubl does not. |
| platform * | string | Target automation platform. |
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
{
"name": "format_code",
"title": "Format code for automation platforms",
"description": "Format and lint JavaScript, Python, or HubL code for Zapier, n8n, Pipedream, Make, or HubSpot. Wraps the source in each platform's runtime shell before formatting so top-level await, bare return, and injected globals don't break the formatter. Returns formatted code plus lint diagnostics.",
"inputSchema": {
"type": "object",
"required": [
"code",
"platform"
],
"properties": {
"code": {
"type": "string",
"description": "Source code to format (≤50KB)."
},
"language": {
"enum": [
"javascript",
"typescript",
"python"
],
"type": "string",
"description": "Defaults to javascript. typescript parses TypeScript on pipedream and reads as javascript elsewhere. zapier, n8n, pipedream, make, and hubspot support python; hubl does not."
},
"platform": {
"enum": [
"zapier",
"n8n",
"pipedream",
"make",
"hubspot",
"hubl"
],
"type": "string",
"description": "Target automation platform."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"diagnostics",
"error"
],
"properties": {
"error": {
"type": [
"string",
"null"
],
"description": "Why the format failed, or null on success."
},
"diagnostics": {
"type": "array",
"items": {
"type": "object"
},
"description": "Lint findings with line and column."
},
"formatted_code": {
"type": "string",
"description": "The formatted source. Absent when the input was refused."
},
"lint_unavailable": {
"type": "boolean",
"const": true,
"description": "Present only when the linter could not run, so an empty diagnostics list is unknown, not clean."
},
"diagnostics_frame": {
"enum": [
"input",
"output"
],
"type": "string",
"description": "Whether diagnostic positions refer to the submitted code or the formatted code."
}
}
},
"annotations": {
"readOnlyHint": true
}
}Ask a natural-language question about codefmt: formatting and linting JavaScript, Python, and HubL for automation platforms (Zapier, n8n, Pipedream, Make, HubSpot). Returns a grounded answer drawn from codefmt's own content with cited source URLs and a confidence score (0-1, how much of the question the answer covers, weighted toward its rarer terms); off-topic or too-weakly-matched questions are refused rather than guessed.
| Parameter | Type | Description |
|---|---|---|
| query * | string | The natural-language question about codefmt. |
{
"name": "ask_codefmt",
"title": "Ask codefmt",
"description": "Ask a natural-language question about codefmt: formatting and linting JavaScript, Python, and HubL for automation platforms (Zapier, n8n, Pipedream, Make, HubSpot). Returns a grounded answer drawn from codefmt's own content with cited source URLs and a confidence score (0-1, how much of the question the answer covers, weighted toward its rarer terms); off-topic or too-weakly-matched questions are refused rather than guessed.",
"inputSchema": {
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "The natural-language question about codefmt."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"answer",
"sources",
"results"
],
"properties": {
"answer": {
"type": "string",
"description": "The grounded answer, or the refusal text."
},
"results": {
"type": "array",
"items": {
"type": "object",
"required": [
"label",
"source",
"score"
],
"properties": {
"label": {
"type": "string"
},
"score": {
"type": "number"
},
"source": {
"type": "string"
}
}
},
"description": "Ranked matching entries."
},
"sources": {
"type": "array",
"items": {
"type": "string"
},
"description": "Cited source URLs."
},
"confidence": {
"type": "number",
"maximum": 1,
"minimum": 0,
"description": "How much of the question the answer covers, weighted toward its rarer terms."
}
}
},
"annotations": {
"readOnlyHint": true
}
}Format (pretty-print or minify) a JSON document, optionally sorting object keys. Number literals are preserved exactly (64-bit IDs safe); parse errors report the exact line and column.
| Parameter | Type | Description |
|---|---|---|
| json * | string | The JSON text to format. |
| indent | string | Indentation: '2' or '4' spaces, 'tab', or 'minify'. Defaults to '2'. |
| sort_keys | boolean | Sort object keys alphabetically. Defaults to false. |
{
"name": "format_json",
"title": "Format a JSON document",
"description": "Format (pretty-print or minify) a JSON document, optionally sorting object keys. Number literals are preserved exactly (64-bit IDs safe); parse errors report the exact line and column.",
"inputSchema": {
"type": "object",
"required": [
"json"
],
"properties": {
"json": {
"type": "string",
"description": "The JSON text to format."
},
"indent": {
"enum": [
"2",
"4",
"tab",
"minify"
],
"type": "string",
"description": "Indentation: '2' or '4' spaces, 'tab', or 'minify'. Defaults to '2'."
},
"sort_keys": {
"type": "boolean",
"description": "Sort object keys alphabetically. Defaults to false."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"required": [
"error"
],
"properties": {
"error": {
"type": [
"string",
"null"
],
"description": "\"line L, col C: message\" on a parse error, or null."
},
"formatted_json": {
"type": "string",
"description": "The formatted document. Absent when the input was refused."
}
}
},
"annotations": {
"readOnlyHint": true
}
}format_code { code, platform, language? } formats JavaScript, Python, or HubL for an automation platform (output { formatted_code, diagnostics, error }). ask_codefmt { query } answers natural-language questions about codefmt with cited sources. format_json { json, indent?, sort_keys? } pretty-prints or minifies a JSON document (output { formatted_json, error }).
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.