此 MCP 可以做什么
Converts and edits text formats, generates diffs and patches, prunes text, estimates LLM costs, and creates or validates llms.txt files.
功能
工具
8
工具
convert
Transform text between JSON, YAML, TOML, and CSV formats. Returns the converted text and input/output character metrics. Note some conversions can be lossy (e.g. JSON to CSV flattens nested structures). Requires a valid API key (Bearer token); billing is per input character â insufficient balance returns HTTP 402. For removing comments use `prune`, for generating llms.txt use `generate`.
只读
幂等
输入模式
{'type': 'object', 'required': ['payload', 'from_format', 'to_format'], 'properties': {'payload': {'type': 'string', 'description': 'Text to convert (1 char min, 10 MiB max).'}, 'to_format': {'enum': ['json', 'yaml', 'toml', 'csv'], 'type': 'string', 'description': 'Target format to convert into.'}, 'from_format': {'enum': ['json', 'yaml', 'toml', 'csv'], 'type': 'string', 'description': 'Source format of the input payload.'}}}
diff
Generate a unified diff between two text versions (the before and after). Returns the diff text plus metrics (lines added, lines removed, output chars). Requires a valid API key (Bearer token); billing is per combined input characters. To apply a diff, use `patch`.
只读
幂等
输入模式
{'type': 'object', 'required': ['text_a', 'text_b'], 'properties': {'text_a': {'type': 'string', 'description': 'First text version (the "before" text).'}, 'text_b': {'type': 'string', 'description': 'Second text version (the "after" text).'}}}
estimate
Estimate the USD cost of an LLM API call using the CWEP four-flow model (request generation, request processing, response generation, response reception). Returns a JSON object with the per-flow cost breakdown, the total, and the pricing source date. Unknown model names return HTTP 422 â check GET /api/v1/pricing on costa.nanotoll.dev for the supported list (no auth needed). Requires a valid API key (Bearer token); billing is per input character.
只读
幂等
输入模式
{'type': 'object', 'required': ['model', 'input_tokens', 'output_tokens'], 'properties': {'model': {'type': 'string', 'description': 'Model name (e.g. gpt-4o).'}, 'input_tokens': {'type': 'integer', 'minimum': 0, 'description': 'Number of input (prompt) tokens.'}, 'output_tokens': {'type': 'integer', 'minimum': 0, 'description': 'Number of output (completion) tokens.'}}}
generate
Generate an llms.txt agent-discovery file from structured service metadata (name, endpoints, overview, links, pricing). Returns the llms.txt content and output metrics. Requires a valid API key (Bearer token); billing is per input character. To check an existing llms.txt for spec compliance, use `validate`.
只读
幂等
输入模式
{'type': 'object', 'required': ['name', 'endpoints'], 'properties': {'name': {'type': 'string', 'description': 'Service name (H1 title of the llms.txt file).'}, 'links': {'type': 'array', 'items': {'type': 'object', 'required': ['title', 'url'], 'properties': {'url': {'type': 'string', 'format': 'uri', 'description': 'Target URL.'}, 'title': {'type': 'string', 'description': 'Display text for the link.'}}}, 'description': 'Optional related links (docs, source, etc.). Each item has title and url.'}, 'pricing': {'type': ['string', 'null'], 'description': 'Pricing summary string (e.g. "$0.0002 per call"). Pass null to omit.'}, 'tagline': {'type': ['string', 'null'], 'description': 'One-line summary of the service, shown as a subtitle below the H1. Pass null to omit.'}, 'overview': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Paragraphs of prose describing the service. Each array element becomes a paragraph in the llms.txt Overview section.'}, 'endpoints': {'type': 'array', 'items': {'type': 'object', 'required': ['method', 'path', 'description'], 'properties': {'path': {'type': 'string', 'description': 'Endpoint path (e.g. /api/v1/squeeze).'}, 'method': {'type': 'string', 'description': 'HTTP method (GET, POST, etc.).'}, 'description': {'type': 'string', 'description': 'What the endpoint does.'}}}, 'description': 'API endpoints to list in the llms.txt. Each item has method, path, and description.'}}}
patch
Apply a unified diff patch to text, producing the transformed output. Returns the patched text. Requires a valid API key (Bearer token); billing is per combined input characters. To generate a diff, use `diff`.
输入模式
{'type': 'object', 'required': ['text', 'patch'], 'properties': {'text': {'type': 'string', 'description': 'Original text to apply the patch to.'}, 'patch': {'type': 'string', 'description': 'Unified diff patch text.'}}}
prune
Strip comments and empty lines from text to reduce token count before sending to an LLM. Returns the pruned text and character metrics. Requires a valid API key (Bearer token); billing is per input character â insufficient balance returns HTTP 402. For format conversion use `convert`, for generating llms.txt use `generate`.
只读
幂等
输入模式
{'type': 'object', 'required': ['payload'], 'properties': {'payload': {'type': 'string', 'description': 'Text to prune (1 char min, 10 MiB max).'}, 'comment_prefix': {'type': 'string', 'description': "Optional. Explicit comment-line prefix to strip outside code fences (e.g. '//' for C-style code). Omit for format-aware pruning: markdown '#' headings are preserved (v101 #12 note), no line stripping on plain text. Max 64 bytes, no control chars."}, 'remove_empty_lines': {'type': 'boolean', 'default': True, 'description': 'If true, empty lines outside code fences are removed.'}}}
read
Fetch a web page and return clean GitHub-flavored markdown at a strict token budget. DOM-density scoring strips boilerplate (CSS, JS, navbars, tracking) â raw HTML averages 80-95% noise. Requires a valid API key (Bearer token); billing is $0.0005 flat per read â insufficient balance returns HTTP 402. Fetch failures return HTTP 422 and are refunded.
只读
可访问外部资源
幂等
输入模式
{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'format': 'uri', 'description': 'URL of the web page to fetch and convert to markdown.'}, 'max_tokens': {'type': 'integer', 'minimum': 1, 'description': 'Optional token budget â\x80\x94 markdown is truncated to this many estimated tokens. Omit for full page.'}, 'include_links': {'type': 'boolean', 'default': True, 'description': 'If true, hyperlinks are kept as markdown links.'}, 'preserve_tables': {'type': 'boolean', 'default': True, 'description': 'If true, HTML tables are preserved as GFM tables.'}}}
validate
Validate an llms.txt payload for spec compliance (H1 title, endpoints section, pricing section, structure). Returns a validation report with errors, warnings, and structural flags. Requires a valid API key (Bearer token); billing is per input character. To generate new llms.txt, use `generate`.
只读
幂等
输入模式
{'type': 'object', 'required': ['content'], 'properties': {'content': {'type': 'string', 'description': 'llms.txt content to validate.'}}}
历史
近期工具变更
已添加
read
2026年9月17日 12:39
已添加
validate
2026年9月17日 12:39
已添加
generate
2026年9月17日 12:39
已添加
patch
2026年9月17日 12:39
已添加
diff
2026年9月17日 12:39
已添加
estimate
2026年9月17日 12:39
已添加
convert
2026年9月17日 12:39
已添加
prune
2026年9月17日 12:39
发现
类似的 MCP 服务器
TinyFn
io.tinyfn/tinyfn
Offers deterministic utility functions for mathematics, conversions, validation, hashing, encoding, arrays, dates, colors, and pa…
hyperion
com.thetempleofdoom.hyperion/hyperion
Acts as a paid MCP tool marketplace and utility gateway with server discovery, HTTP and JavaScript tools, research, data conversi…
Andreax
io.github.moralito311-andr/andreax
Offers pay-per-call AI services for inference, agent and workflow design, OCR and transcription, code generation and review, clas…
Vee3
io.github.Vee3io/vee3
Manages Clerk authentication infrastructure, including users, organizations, domains, sessions, tokens, OAuth, SSO, machines, per…
GripForge
io.github.gripforgeai/mcp
Generates, rigs, animates, analyzes, and packages game characters, weapons, armor, effects, environments, and engine-ready assets.
Courier
io.github.trycourier/courier
Provides notification delivery infrastructure for users, tenants, lists, templates, preferences, journeys, automations, brands, a…
IA-QA — 130+ QA & Dev Tools for AI Agents
io.github.JcJamet/ia-qa-toolbox
Provides deterministic QA, evaluation, testing, code analysis, prompt and RAG checks, model comparison, and web security diagnost…
apis-io
io.apis/apis-io
Provides catalog search, comparison, scoring, enrichment, lists, and dataset exports for APIs, providers, specifications, workflo…