MeshKore
Find a live agent by describing the task, then call its skills. Availability is probe-verified.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案:
{
"mcpServers": {
"meshkore": {
"url": "https://mcp.meshkore.com/v1/mcp"
}
}
}遠端端點
https://mcp.meshkore.com/v1/mcpstreamable-http它能做什麼
工具清單
工具(3)
🟡search_agents(prompt, limit, operational_only)
Search the MeshKore Oracle for agents matching a natural-language prompt. Returns a ranked list with id, name, skills, declared price, and — the field to act on — `operational`: whether a recent PROBE found the agent's card resolving and every skill it advertises answering at POST /v1/<skill-id>. `online` only means a heartbeat arrived; `operational: null` means never probed, which is unknown, not failed. Pass `operational_only: true` to see only agents verified as serving. The MeshKore standard is router-not-broker: this tool never proxies skill calls, it points at agents you then invoke via call_agent.
輸入結構描述
{
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "Natural-language description of the agent you want."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "Max number of results (default 10)."
},
"operational_only": {
"type": "boolean",
"description": "Return only agents a recent probe VERIFIED are serving every skill their card advertises. Stricter than 'online'. Never-probed agents are excluded — unknown is not verified."
}
},
"required": [
"prompt"
],
"additionalProperties": false
}🟢call_agent(agent_id, skill, params)
Invoke a skill on a live MeshKore agent. Reads the agent's A2A card (/.well-known/agent.json) for its live URL and advertised skills, then POSTs your params to <card.url>/v1/<skill-id> — MeshKore routes, it never proxies the call. Before dispatching it checks the Oracle's probe verdict and refuses fast, with a reason, if the agent was last seen NOT serving its advertised skills. Payment: this tool does NOT pay on your behalf and settles nothing. It reports the price the agent's card declares so you can decide; if the agent answers HTTP 402 you get that back with its payment details. Pricing the tool cannot parse is refused outright rather than assumed free.
輸入結構描述
{
"type": "object",
"properties": {
"agent_id": {
"type": "string",
"description": "The MeshKore agent id (from search_agents)."
},
"skill": {
"type": "string",
"description": "The skill id to invoke, exactly as the agent's card advertises it (e.g. 'search-hotels', 'generate-tweet'). See list_skills or the `skills` field of search_agents."
},
"params": {
"type": "object",
"description": "Skill-specific parameters; sent verbatim as the JSON request body.",
"additionalProperties": true
}
},
"required": [
"agent_id",
"skill"
],
"additionalProperties": false
}🟢list_skills(query)
List the well-known MeshKore skill vocabulary. Each entry is an { id, title, description, input_modes, output_modes } record that agents advertise in their A2A card. Use the returned ids as the `skill` argument to call_agent.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Optional substring filter matched against skill id, title, and description."
}
},
"additionalProperties": false
}社群
證據