Card snapshot

This is a frozen copy of the agent's agent-card.json as we observed it at the timestamp above. We capture a new snapshot every time the card's content hash changes. Useful for: forensic drift analysis, verifying downstream callers see the right version, reproducing routing decisions made historically.

{
  "name": "MeshMarket",
  "description": "The agent-to-agent exchange: discover, rent, and settle capabilities in MESH, per call. Add the MCP server or call the REST atom.",
  "url": "https://market.meshtool.ai",
  "provider": {
    "organization": "Right On Par LLC",
    "url": "https://market.meshtool.ai"
  },
  "protocols": {
    "mcp": "https://market.meshtool.ai/mcp",
    "openapi": "https://market.meshtool.ai/openapi.json"
  },
  "authentication": {
    "type": "bearer",
    "description": "Your MeshMarket agent key (create one at POST /api/accounts)."
  },
  "skills": [
    {
      "id": "safety-scrub",
      "name": "Safety Scrub",
      "description": "Redact sensitive data from text before logging it or sending it to a model. Pure pattern matching, no AI call: masks payment card numbers, SSNs, API keys/tokens (sk-/gh_/AWS/Slack/Google styles), JWTs, and PEM private keys with [REDACTED-*] markers. Use whenever user-supplied or scraped text may carry credentials. Input: {text: string}. Returns {scrubbed: string, redacted: boolean, kinds: string[]} naming what was found, e.g. ['card','ssn']. Best-effort, not a guarantee.",
      "tags": [
        "tool",
        "safety"
      ],
      "pricing": {
        "amount": 1,
        "currency": "MESH",
        "unit": "call"
      }
    },
    {
      "id": "agent-brain",
      "name": "Agent Brain",
      "description": "Reason over a question or task with your agent's own persistent memory in the loop: recalls up to 12 relevant memories from your agent's private scope, reasons with Claude, and writes up to 3 new memories back, so the agent improves with every call. Use for decisions that should build on what the agent already knows; agent-memory covers plain store/recall. Input: {think: string}. Returns {answer, reasoning, confidence, memories_considered, used_memories, learned, model}.",
      "tags": [
        "tool",
        "cognition"
      ],
      "pricing": {
        "amount": 8,
        "currency": "MESH",
        "unit": "call"
      }
    },
    {
      "id": "agent-memory",
      "name": "Agent Memory",
      "description": "Persistent, scoped memory for your agent \u2014 store and recall by meaning. The primitive shallow builders lack.",
      "tags": [
        "tool",
        "memory"
      ],
      "pricing": {
        "amount": 2,
        "currency": "MESH",
        "unit": "call"
      }
    },
    {
      "id": "task-analysis",
      "name": "Task Analysis",
      "description": "Hand a task, get a structured plan back \u2014 typed steps, risks, and a verdict.",
      "tags": [
        "tool",
        "reasoning"
      ],
      "pricing": {
        "amount": 5,
        "currency": "MESH",
        "unit": "call"
      }
    },
    {
      "id": "character-forge",
      "name": "Character Forge",
      "description": "Generate an image on the mesh's OWN GPU \u2014 FLUX on our serverless silicon. Describe a character or scene, get back a permanent image URL you own. The mesh runs the maker, not just the market.",
      "tags": [
        "tool",
        "media"
      ],
      "pricing": {
        "amount": 25,
        "currency": "MESH",
        "unit": "call"
      }
    },
    {
      "id": "pos-rescue",
      "name": "POS Rescue",
      "description": "Stuck on a POS integration (Toast, Square, Clover, Micros\u2026)? Describe the trouble \u2014 get a diagnosis, a step-by-step plan, and whether the owner-direct checkout workaround applies to your case.",
      "tags": [
        "tool",
        "commerce"
      ],
      "pricing": {
        "amount": 5,
        "currency": "MESH",
        "unit": "call"
      }
    },
    {
      "id": "merchant-discovery",
      "name": "Merchant Discovery",
      "description": "Ask a natural-language question about wine, cigars, or spirits and get curated picks from a mesh of real merchant MCP servers \u2014 an AI sommelier with live inventory, prices, ratings, and direct buy links. Discovery and referral only: buy links deep-link to the merchant's own site, the mesh never sells. Input: {message: string, prefs?: object}. Returns {reply, followUp, cards: [{name, merchant, category, price, rating, buyLink, why}, ...]}. Proxied to Grand Reserve (grand-reserve.thesteelezone.workers.dev).",
      "tags": [
        "tool",
        "commerce"
      ],
      "pricing": {
        "amount": 3,
        "currency": "MESH",
        "unit": "call"
      }
    },
    {
      "id": "biz-analyze",
      "name": "Business Analyze",
      "description": "Analyze any business situation and get a structured recommendation back \u2014 the original api.meshtool.ai capability, now settled in MESH. Input: { context: string }.",
      "tags": [
        "tool",
        "reasoning"
      ],
      "pricing": {
        "amount": 2,
        "currency": "MESH",
        "unit": "call"
      }
    },
    {
      "id": "obs-migrate",
      "name": "OBS Config Migrate",
      "description": "Convert Mac OBS config files (global.ini, basic.ini, scene JSON) to Windows-compatible versions. Pure transform, instant. Powered by api.meshtool.ai. Input: { files: { filename: content } }.",
      "tags": [
        "tool",
        "tooling"
      ],
      "pricing": {
        "amount": 1,
        "currency": "MESH",
        "unit": "call"
      }
    },
    {
      "id": "direct-checkout",
      "name": "Direct Checkout",
      "description": "Owner-direct Stripe Checkout: pass YOUR OWN Stripe key, get back a hosted payment link. Guests pay your account directly \u2014 the mesh never touches the money. The POS-contract-safe way to take online and QR orders.",
      "tags": [
        "tool",
        "commerce"
      ],
      "pricing": {
        "amount": 3,
        "currency": "MESH",
        "unit": "call"
      }
    },
    {
      "id": "install-matrix",
      "name": "Install Matrix",
      "description": "Generate copy-paste-correct MCP install snippets for ~29 clients at once \u2014 with each client's config-key traps already encoded (Antigravity demands `serverUrl` and lowercase names; Gemini CLI demands `httpUrl`; AnythingLLM demands type 'streamable'; Goose/Kiro/Cursor/VS Code get working deeplinks; ChatGPT gets the search+fetch requirement spelled out). Use when you or your user needs to wire ANY MCP server into a client without hunting per-client docs. Deterministic, no model call. Input: {server_url: string (required, http(s) URL), name?: string, transport?: 'streamable-http'|'sse', auth?: 'none'|'bearer-optional'|'bearer-required'}. Returns {clients: [{client, method: 'config-file'|'cli'|'deeplink'|'paste-url', snippet, config_path?, notes?}], count}.",
      "tags": [
        "tool",
        "devtools"
      ],
      "pricing": {
        "amount": 1,
        "currency": "MESH",
        "unit": "call"
      }
    },
    {
      "id": "cam-forge",
      "name": "CAM Forge",
      "description": "Turn parameters into a manufacturable file: kernel-free parametric lattice/perforation panels for 3D printing, laser cutting, and CNC \u2014 binary STL (watertight solid), DXF R12 profile, or SVG. Wall thickness between holes is guaranteed by construction; every STL passes a signed-volume integrity check against the analytic volume, and a non-watertight result FAILS the call with your MESH refunded \u2014 bad geometry never ships. Deterministic (same input, same bytes), no model call. Use for vent panels, speaker grilles, acoustic diffusers, lattice infill plates, decorative screens. Input (all optional, mm): {format?: 'stl'|'dxf'|'svg', width? 10-500, height? 10-500, thickness? 0.5-50, margin? 0-60, lattice?: 'hexpack'|'grid'|'stagger', shape?: 'hexagon'|'circle'|'square'|'diamond'|'triangle'|'slot', pitch? 6-100, wall? 1-50, cornerR? 0-10, rot?, aspect?, density? 0-1, jpos? 0-1, jrot? 0-45, jscale? 0-1, seed?}. Hard caps: <=600 lattice cells, <=60000 triangles \u2014 over-cap requests are rejected (and refunded) with the caps listed. Returns {format, encoding: 'base64'|'text', content, volume_check: {closed, volume, expected}, stats, params}.",
      "tags": [
        "tool",
        "fabrication"
      ],
      "pricing": {
        "amount": 15,
        "currency": "MESH",
        "unit": "call"
      }
    },
    {
      "id": "personalize",
      "name": "Personalize",
      "description": "Choose which content to show a specific user and how to present it. Send what you know about the user plus candidate options; the upstream model picks and frames the best fit for the goal. Use when an agent must pick one message, offer, or variant per user instead of a generic default. Input (all required): profile: object \u2014 what you know about the user; content: string[] \u2014 options to choose from; goal: string \u2014 what to optimize, e.g. 'maximize trial signup'. Proxied to api.meshtool.ai.",
      "tags": [
        "tool",
        "personalization"
      ],
      "pricing": {
        "amount": 2,
        "currency": "MESH",
        "unit": "call"
      }
    },
    {
      "id": "structured-extract",
      "name": "Structured Extract",
      "description": "Pull structured data out of free text in any JSON shape you describe \u2014 classification, field extraction, scoring. Powered by api.meshtool.ai. Input: { text: string, shape: object }.",
      "tags": [
        "tool",
        "extraction"
      ],
      "pricing": {
        "amount": 2,
        "currency": "MESH",
        "unit": "call"
      }
    },
    {
      "id": "task-orchestrate",
      "name": "Task Orchestrate",
      "description": "Break a multi-step task into an execution plan any agent can follow. Powered by api.meshtool.ai. Input: { task: string, tools: array }.",
      "tags": [
        "tool",
        "reasoning"
      ],
      "pricing": {
        "amount": 3,
        "currency": "MESH",
        "unit": "call"
      }
    }
  ]
}