Gildara

Prompt infrastructure for AI agents—resolve, compose, and manage reusable prompts and briefs through OAuth-secured MCP tools.

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

接入信息

传输形态: http
鉴权方式: 鉴权未知
端点: https://mcp-server--gildara-io.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "Gildara": {
      "url": "https://mcp-server--gildara-io.run.tools"
    }
  }
}

能力清单

工具	说明
list_prompts	List all prompts in your Gildara vault. Returns titles, IDs, and categories. If connected via OAuth, no API key needed.
search_prompts	Search your Gildara vault semantically by meaning, not just keywords. Returns the most relevant prompts for a natural-language query (e.g. "reviewing code for security issues", "summarizing customer feedback"). Ranked by vector similarity over title, description, category, tags, and content. Use this first before list_prompts when looking for a prompt that matches a concept.
get_prompt	Get details of a specific prompt including its content.
resolve_prompt	Resolve a prompt into its compiled form with operating contract sections assembled. This is what you should use as a system prompt.
create_prompt	Save a new prompt to your Gildara vault.
save_brief	Create a Brief and dispatch it to a named agent. Use when the user wants to send work to a specific agent (phrases like 'send this to gevorg', 'dispatch this', 'have [agent] do this'). Compose `body` in the second person addressing the agent — it is FROZEN as the agent's instruction packet and the agent has no access to this conversation. Returns immediately after dispatch; the agent's result arrives asynchronously. Default classification 'internal'; only set 'confidential' on explicit user signal. Do NOT write return-result instructions in the body — Gildara auto-appends a 'Returning your result' footer with the exact POST endpoint, brief_id, scope, and payload shape before freezing. Focus `body` on the WORK; the system handles the return contract.
get_brief_result	Fetch the result an agent submitted for a previously-dispatched Brief. Use when the user asks 'what did [agent] say about [brief]?', 'show me the result', 'did gevorg respond yet?', or references a brief_id like 'brf_xxxxxxxx'. Returns null-equivalent text if the result hasn't arrived yet — that's a valid state, not an error.
list_returned_briefs	List briefs that have results returned from their agents (status='returned'), most recent first. Use when the user asks 'what results are waiting for me?', 'any agent responses?', 'show me completed briefs', 'what did my agents send back?'. Returns summaries (title, agent, returned time) — use get_brief_result(brief_id) to fetch the actual result text for a specific brief.
append_memory	Append content to an existing prompt. Creates a new version with the appended content.
list_blueprints	Browse available prompt templates. No API key needed.
draft_prompt	Turn a messy brain dump into a clean, structured prompt using AI.

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。