Agentskin
This is a local proxy layer that sits between Claude and any HTTP endpoint you're hitting. It exposes two tools: fetch_optimized_data pulls from APIs or web URLs and strips out verbose keys you don't need, returning compact Markdown instead of bloated JSON, and skin_reasoning compresses natural language by removing filler words. You pass in the URL plus optional signals (keys to keep) and aliases (renames for consistency). The repo claims 70% token reduction on typical API responses. It includes SSRF protection, rate limiting, and blocks cloud metadata endpoints. Reach for this when you're burning tokens on repetitive API calls with huge payloads where you only need a handful of fields, or when chaining multiple web requests in a reasoning loop.
- tools
- 2
- auth
- Secret needed
- transport
- STDIO
- env vars
- 4
- last updated
- Mar 13, 2026
Tools
2 toolsPublic tool metadata for what this MCP can expose to an agent.
fetch_optimized_dataFetches any API or Web URL and returns a token-optimized "Skin."
Fetches any API or Web URL and returns a token-optimized "Skin."
No parameter schema in public metadata yet.
skin_reasoningOptimizes natural language text by removing linguistic noise (hedging, filler).
Optimizes natural language text by removing linguistic noise (hedging, filler).
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
BRAVE_SEARCH_API_KEYsecretBrave Search API Key
SERPER_API_KEYsecretSerper.dev Search API Key
TAVILY_API_KEYsecretTavily Search API Key
APILAYER_KEYsecretMediaStack API Key
Readme
AgentSkin
Context middleware for AI agents. AgentSkin removes low-value API, JSON, and terminal noise before it enters model context.
The frozen AgentSkin 5.1 offline core evaluation also has an accepted Sparse Env execution path. AgentSkin preserves the workload correctness contract while Sparse Env owns cold/warm environment selection and lifecycle; see agentskin/docs/SPARSE_ENV.md.
What it does
AgentSkin has three primary workflows:
compress— one front door that auto-detects JSON, CLI output, or plain text.fetch_optimized_data— fetches a public URL and applies URL-specific pruning rules when available.reduce— compacts terminal output using Tokenjuice's rule-driven reducers.
Five advanced tools remain for compatibility and diagnostics: apply_json_semantic, classify_url, strip_ansi, estimate_tokens, and skin_reasoning.
Quick start
npx -y agentskin@latest
MCP config:
Details
- Repository
- github.com/shawn5cents/agentskin
- Category
- Data & Analytics
- Package
agentskin- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
Related Data & Analytics MCP servers
View all
Dart Querystandardbeagle/dart-queryDart AI task management MCP with batch operations, DartQL selectors, CSV import, zero context rot0stars
Suparse Document Processingsuparse/suparse-mcpExtract data, create schemas, and export results from PDFs and documents with Suparse AI OCR.0stars
Incidentoracletooloracle/incidentoracleIncidentOracle - 12-tool incident management MCP: triage, BaFin DORA reporting, RCA.0stars
Repology Mcp Servertschoonj/repology-mcp-serverMCP server that provides access to Repology package repository data0stars
Turbometrics Mcpturbopress-de/turbometrics-mcpWebsite performance monitoring: scans, Core Web Vitals, RUM data and alerts.0stars
JSONShelfwalkojas-boop/jsonshelfDeterministic JSON repair, validate, example-gen, schema-coerce for agents. Zero LLM, sub-10ms.0stars