addrbookFor publishers
← The evidence ledger

Evidence row 566062

Observed , by probe.mcp/1.

Kind
mcp.tools
About
endpoint 8c0d0d94-0a84-4d91-ac95-7af9c2e62a1c
Recorded
Previous row
None: the first of its kind about this subject
Body SHA-256
8b9c18913b439d6cf41f0b14c9080476b0f902ee56935600bad8b0eebd12f60b
Leaf
0x58d8cd8683285946476c5cfd6dad5f74cc43b9e90418e23e756e23dd3ebcc7c9

What was observed

{
  "count": 4,
  "tools": [
    {
      "description": "Get one skill as Markdown: summary, metadata, install command and the full skill file. `owner` and `name` are the last two segments of a skill's pageUrl (https://skillagent.dev/skill/{owner}/{name}).",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "name": {
            "description": "Skill slug from the pageUrl.",
            "type": "string"
          },
          "owner": {
            "description": "GitHub owner, e.g. anthropics.",
            "type": "string"
          }
        },
        "required": [
          "owner",
          "name"
        ],
        "type": "object"
      },
      "name": "get_skill"
    },
    {
      "description": "Exact installation instructions for one skill on one agent: the install command(s) when one exists, otherwise the file to create (path relative to the project root) with its content. This tool does not install anything; apply the result yourself, and only after showing the user the skill and getting their approval. Includes the safety summary. Refuses (isError) when the skill's safety scan is at \"warning\". `owner` and `name` are the last two segments of a skill's pageUrl.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "agent": {
            "description": "The agent to install into, e.g. claude-code, cursor, codex.",
            "enum": [
              "claude-code",
              "claude-desktop",
              "vscode-copilot",
              "cursor",
              "windsurf",
              "cline",
              "zed",
              "jetbrains",
              "gemini-cli",
              "codex",
              "aider",
              "continue",
              "replit",
              "amazon-q",
              "tabnine",
              "sourcegraph-cody",
              "devin",
              "universal"
            ],
            "type": "string"
          },
          "name": {
            "description": "Skill slug from the pageUrl.",
            "type": "string"
          },
          "owner": {
            "description": "GitHub owner, e.g. anthropics.",
            "type": "string"
          }
        },
        "required": [
          "owner",
          "name",
          "agent"
        ],
        "type": "object"
      },
      "name": "install_skill"
    },
    {
      "description": "Recommend skills for a project from a description of it: languages, frameworks or dependencies (e.g. names from package.json or requirements.txt), a task, and the agent the user runs. Returns a ranked shortlist; each entry has the skill record and a `why` explaining the match (matched terms, fit for the agent, freshness, quality, safety). Ranking is deterministic. Skills whose safety scan is at \"warning\" or whose source is gone are excluded, and the result says how many were.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "agent": {
            "description": "The agent the user runs; skills made for it rank higher.",
            "enum": [
              "claude-code",
              "claude-desktop",
              "vscode-copilot",
              "cursor",
              "windsurf",
              "cline",
              "zed",
              "jetbrains",
              "gemini-cli",
              "codex",
              "aider",
              "continue",
              "replit",
              "amazon-q",
              "tabnine",
              "sourcegraph-cody",
              "devin",
              "universal"
            ],
            "type": "string"
          },
          "dependencies": {
            "description": "Package names from a manifest, e.g. [\"@playwright/test\", \"prisma\"].",
            "items": {
              "type": "string"
            },
            "maxItems": 30,
            "type": "array"
          },
          "frameworks": {
            "description": "Frameworks and tools, e.g. [\"next.js\", \"playwright\"].",
            "items": {
              "type": "string"
            },
            "maxItems": 20,
            "type": "array"
          },
          "languages": {
            "description": "Programming languages, e.g. [\"typescript\", \"python\"].",
            "items": {
              "type": "string"
            },
            "maxItems": 10,
            "type": "array"
          },
          "limit": {
            "default": 8,
            "maximum": 20,
            "minimum": 1,
            "type": "integer"
          },
          "task": {
            "description": "What the user wants to do, e.g. \"write e2e tests\".",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "recommend_skills"
    },
    {
      "description": "Search the SkillAgent catalogue of AI agent skills, rules files and MCP servers. Returns matching skills with description, format, stars, quality score, freshness, page URL and install command.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "category": {
            "description": "Category, e.g. development, data-analytics, security.",
            "type": "string"
          },
          "format": {
            "description": "Skill format, e.g. skill-md, claude-md, agents-md, cursorrules, mcp-server.",
            "type": "string"
          },
          "health": {
            "description": "Filter by repository freshness or reachability.",
            "enum": [
              "fresh",
              "aging",
              "stale",
              "abandoned",
              "alive",
              "gone"
            ],
            "type": "string"
          },
          "limit": {
            "default": 10,
            "maximum": 50,
            "minimum": 1,
            "type": "integer"
          },
          "offset": {
            "default": 0,
            "minimum": 0,
            "type": "integer"
          },
          "platform": {
            "description": "Agent platform, e.g. claude-code, cursor, codex, vscode-copilot, windsurf.",
            "type": "string"
          },
          "query": {
            "description": "Keywords matched against name, description, owner and tags.",
            "type": "string"
          },
          "sort": {
            "default": "score",
            "enum": [
              "score",
              "stars",
              "updated",
              "name"
            ],
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "search_skills"
    }
  ]
}

What the leaf hashes

{"body":"8b9c18913b439d6cf41f0b14c9080476b0f902ee56935600bad8b0eebd12f60b","id":566062,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793138350133221,"prev":null,"subject":"8c0d0d94-0a84-4d91-ac95-7af9c2e62a1c","subject_kind":"endpoint"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of (273461 rows).

  1. 0x58d8f79da463ea5b23aba607c8b5a27a5fa8e76b0140136a1ee9fc6004d16729
  2. 0x27b3cab1acbd76cc1523dbf36b251f3a40e48c93b600d9fc4f545e85886eda2b
  3. 0x70b38b6882f038c8d94ad63e85e9807fd694dbc5fde8a6403b2d5830e1ea0a0d
  4. 0xab6e61acc6c24ff4af87f6a33c977775120d6197c4e8e2f3486f54fbcbcd5f4c
  5. 0x6533b2909bd715b425f26316a7afe273bd85fd84f6bc8bb092b4dda36a1910fc
  6. 0x013f276937dcd4b8878862acb2794a56c528c81e6c46a59ecb950cb32df456f0
  7. 0xd36a87bc27cca460d77ecbe02a16fed549ef8c2f5f532f4f37b1f98a4e597367
  8. 0xa9858d74dc282da05c5a96f8823e29d926a83261f289939c50cf971bbf095ea8
  9. 0x944e7aaeea420d46eb47a7a485676737373bb2cf7381786681321744a636f88a
  10. 0x4b7c11c4490deca87cecc8066e3eb2b10f5829522d2ca6e53f1f1a7172ec532e
  11. 0x095b40edf800595a91733b7d7641dc11c53f74bc29c345d97d171068bd13ee53
  12. 0x6f9c2e17fd073d07da42da76c8ca2f200b30027f0378b0d9628f8fac6f48cd16
  13. 0x5b3213451efe1e2950dd287afaede00cc8a45dfd9721ef9b3d698bde1eeb9909
  14. 0x674bc1173d39130be4d15bbfc7327f8a8af87eb251e54c8d4409c7e840b9e538
  15. 0xb78ea6a255dd06e2f402a1a733bca392fa6243920bcba95e8b80bdfc6ce5f553
  16. 0x3ed50f053eca72dfd3a9d45a11935240bfe691e57835c367ddebe2cbc49efe9d
  17. 0x0e01aa9525097570a6edaf32bfc959de57bf5c24317cf10c0716affea85ca60d
  18. 0xa20d48798a34aba12eb9c7297722982d910f06c148f5e27ac59307422964a585
  19. 0x9fc354c0ea3efc3f1b6548bb77ea902a50f2c9647647ea61592efce2bd795699
Day root
0xdd77e5e99da32c3f154180d63e3c3e6fe11e896a2c6896412ef6b5c4bcf7e795
Chained
0x23bb4dfd09f55c15ac3962f53578e02c6114d5bfd9bb451cf8794fb6e2817ef4
Published
On Arc Testnet, block 69414147: 0xb2ebd83aafeb765a0ce66e76aefb133ed06606c98038fd56191e2bcd1dcb77b4

How to check it · This row as JSON