Gildara

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

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • 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", "summar
  • Get Prompt: Get details of a specific prompt including its content.

What data it sees

Do you need an account

No: the server works without sign-in

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

How to connect

How to connect Gildara to Claude

The server address to paste into Claude settings:

https://mcp-server--gildara-io.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Gildara to ChatGPT

The server address to paste into ChatGPT settings:

https://mcp-server--gildara-io.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Gildara to Cursor

The server address to paste into Cursor settings:

https://mcp-server--gildara-io.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (11)

Raw names from tools/list. Only developers need these.

list_promptsList all prompts in your Gildara vault. Returns titles, IDs, and categories. If connected via OAuth, no API key needed.
search_promptsSearch 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_promptGet details of a specific prompt including its content.
resolve_promptResolve a prompt into its compiled form with operating contract sections assembled. This is what you should use as a system prompt.
create_promptSave a new prompt to your Gildara vault.
save_briefCreate 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_resultFetch 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_briefsList 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_memoryAppend content to an existing prompt. Creates a new version with the appended content.
list_blueprintsBrowse available prompt templates. No API key needed.
draft_promptTurn a messy brain dump into a clean, structured prompt using AI.