gildara
Connect your AI tools to your prompt vault. Gildara gives agents structured operating contracts: prompts with roles, tools, stop conditions, and output schemas, fetched at runtime via API. 6 tools: list, get, resolve, run (with auto-repair), create prompts, and browse agent blueprints.
README
@gildara/mcp-server
MCP server for Gildara — bring your prompt vault into any AI tool.
What it does
Connects your Gildara prompt library to Claude Desktop, Cursor, Windsurf, and any MCP-compatible tool. Your AI assistant can:
- List prompts — browse your vault
- Resolve prompts — get compiled system prompts with operating contracts assembled
- Run prompts — execute with auto-repair (JSON schema validation + retry)
- Create prompts — save new prompts from your AI session
- Browse blueprints — see pre-built agent templates
Setup
1. Get your API key
For agents (no browser needed):
curl -X POST https://gildara.io/api/v1/provision \
-H 'Content-Type: application/json' \
-d '{"agent_label": "my-agent"}'
Returns an API key (pvk_...) instantly. No signup required.
For humans: Go to gildara.io/account and create an API key with the agent-standard preset.
2. Add to Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"gildara": {
"command": "npx",
"args": ["-y", "@gildara/mcp-server"],
"env": {
"GILDARA_API_KEY": "pvk_your_key_here"
}
}
}
}
3. Add to Cursor
Edit .cursor/mcp.json in your project root:
{
"mcpServers": {
"gildara": {
"command": "npx",
"args": ["-y", "@gildara/mcp-server"],
"env": {
"GILDARA_API_KEY": "pvk_your_key_here"
}
}
}
}
4. Add to Claude Code
claude mcp add gildara -- npx -y @gildara/mcp-server
Then set GILDARA_API_KEY in your environment.
Tools
| Tool | Description |
|---|---|
list_prompts |
List all prompts in your vault |
get_prompt |
Get prompt details and operating contract config |
resolve_prompt |
Get compiled system prompt with contract sections |
run_prompt |
Run prompt through AI with auto-repair |
create_prompt |
Create a new prompt |
list_blueprints |
Browse agent blueprint templates |
Example usage
Once connected, just tell your AI:
"List my Gildara prompts" "Resolve my code-review-agent prompt with the code_diff variable" "Run the security-audit prompt against this code" "Save this prompt to my Gildara vault"
Environment variables
| Variable | Required | Description |
|---|---|---|
GILDARA_API_KEY |
Yes | Your API key (pvk_...). Get one instantly: curl -X POST https://gildara.io/api/v1/provision -H "Content-Type: application/json" -d '{"agent_label":"my-agent"}' |
GILDARA_BASE_URL |
No | Override API URL (default: https://gildara.io) |
Getting a key without a browser
No signup required. Run this to get an API key in seconds:
curl -X POST https://gildara.io/api/v1/provision \
-H 'Content-Type: application/json' \
-d '{"agent_label": "my-agent"}'
The response includes your api_key (starts with pvk_), a link code for your human owner, and your account ID. Set the key as GILDARA_API_KEY and you're ready.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.