gildara
Gildara MCP
One prompt vault. Every agent. Zero setup. Give Claude, Cursor, Windsurf, and Claude Code a shared, searchable prompt library that survives across chats, machines, and tools.
{ "mcpServers": { "gildara": { "command": "npx", "args": ["-y", "@gildara/mcp-server"] } } }Paste into claude_desktop_config.json, restart Claude — your Gildara tools appear in Claude's tool list. No signup. No API key. The server auto-provisions a free agent on first run and prints a one-click link code to pair it with your account later.

→ Get started at gildara.io — pair your auto-provisioned agent to sync your vault and unlock Pro.
What your AI can do
Search prompts semantically — find by meaning, not just keywords (Gemini embeddings).
Resolve + run prompts — compiled system prompts with operating-contract sections assembled, auto-repair on JSON schema failures.
Create + append — save new prompts, or append persistent facts to memory-type prompts.
Dispatch briefs to agents — say "send this to gevorg" and the MCP server creates a Brief, ships it as a
.mdattachment to your paired Telegram chat, and @mentions the target agent's bot. One call closes the sketch-in-chat → agent-on-another-box → result-in-chat loop. See docs/briefs/dogfood-rollout-v0.md for the agent-side integration recipe.Browse 48+ blueprints — pre-built agent templates.
Related MCP server: Promptibus MCP
Setup
No API key required on first run. As of v0.6.0, the MCP server auto-provisions a new agent account on first startup if no
GILDARA_API_KEYis set, and caches the key at~/.gildara/auto-key.jsonfor future runs. Skip to "Add to Claude Desktop" below — zero curl required.On first run, the server prints a link code to stderr (visible in Claude Desktop's MCP logs). Visit
https://gildara.io/link?code=XXXXXXto pair the auto-provisioned agent with your human account and inherit your subscription tier.
1. (Optional) Use an existing API key instead of auto-provisioning
Skip this whole section if you're happy with auto-provisioning.
Otherwise, get a key one of these ways:
Manual provision via API:
curl -X POST https://gildara.io/api/v1/provision \
-H 'Content-Type: application/json' \
-d '{"agent_label": "my-agent"}'From the web: Go to gildara.io/account and create an API key with the agent-standard preset.
Then set GILDARA_API_KEY in your MCP config (see examples below).
2. Add to Claude Desktop
Edit your claude_desktop_config.json. No env block needed for auto-provision:
{
"mcpServers": {
"gildara": {
"command": "npx",
"args": ["-y", "@gildara/mcp-server"]
}
}
}Or, with an existing key:
{
"mcpServers": {
"gildara": {
"command": "npx",
"args": ["-y", "@gildara/mcp-server"],
"env": {
"GILDARA_API_KEY": "pvk_your_key_here"
}
}
}
}3. Add to Cursor
One click:
Or manually: edit .cursor/mcp.json in your project root using the same configuration as Claude Desktop (with or without the env block — same rules apply).
4. Add to Claude Code
Run this in your terminal:
claude mcp add gildara -- npx -y @gildara/mcp-serverAuto-provision works here too. Set GILDARA_API_KEY in your environment only if you want to use an existing key.
5. Add to Claude Chat (claude.ai)
Gildara supports Remote MCP via HTTP/SSE.
Go to Settings > Connectors in Claude Chat.
Select "Add custom connector".
Name: Gildara Vault.
Remote MCP server URL:
https://gildara.io/api/mcp/mcp.Authentication: OAuth 2.1 (you will be redirected to the Gildara consent page to authorize).
Tools
Tool | Description |
| Semantic search over your vault using Gemini embeddings |
| List all prompts in your vault |
| Get prompt details and operating contract config |
| Get compiled system prompt with variable substitution |
| Run prompt through AI with auto-repair |
| Create a new prompt |
| Add info to an existing memory-type prompt |
| Dispatch a brief to a named agent (MD attachment via Telegram, @mention routes to the right bot) |
| Browse 48+ agent blueprint templates |
| Get the URL to link this agent's vault to a human Gildara account |
Example usage
Once connected, just tell your AI:
"Search my vault for prompts related to security audits."
"Resolve my code-review-agent prompt with the
code_diffvariable.""Run the security-audit prompt against this code."
"Append this preference to my 'Personal Context' memory: I prefer TypeScript over JavaScript."
"Send this to gevorg: analyze last week's Meta Ads performance and flag the bottom 3 campaigns."
Local-First Support
Gildara features a local-first architecture. The MCP server automatically caches resolved prompts to ~/.gildara/cache/ to ensure your agents remain functional even if the Gildara API is temporarily unreachable.
Environment variables
Variable | Required | Description |
| No | Your API key ( |
| No | Override API URL (default: |
License
MIT
Contributing / Maintainers
This package is the stdio MCP server. A sibling HTTP server lives at app/api/mcp/[transport]/route.ts in the parent monorepo (powers the Claude.ai native connector). Both must stay at parity — tool names, argument schemas, response text.
Before adding, removing, or changing a tool here, read docs/MCP_INTEGRATION_CONTRACT.md and run npm run test:unit from the monorepo root to verify parity.
This server cannot be deployed
Maintenance
Related MCP Connectors
Git-backed platform for skills, tools, and context for AI agents
Self-hosted AI prompt library: prompts, collections, tags, teams, chains. 29 MCP tools for agents.
- SetForkOAuthcom.setfork
Runnable, versioned lists for agents: tools, prompts and lists as resources. Git under the hood.
- SkilderOAuthai.skilder
One place to build, share, and govern the skills and tools your AI agents use at work.
Related MCP Servers
- FlicenseNot gradedqualityAmaintenanceSelf-hosted AI prompt library with collections, tags, version history, team collaboration and scoped API keys (pvlt_\*) with allowed_tools whitelist. OAuth 2.1 discovery + 30 tools for Claude/Cursor/Windsurf.-
- AlicenseAqualityCmaintenanceProvides AI agents with structured knowledge about 67+ generative AI models, including model recommendations, prompt formatting, parameter guidance, and validation. It acts as a prompt engineering co-pilot that helps agents use their existing tools more effectively.1262 npm3MIT
- AlicenseAqualityBmaintenanceLocal AES-256-GCM encrypted vault for AI agents. Resolve {{PLACEHOLDER}} secrets in prompts at runtime — LLMs never see real API keys. Argon2id key derivation, zero cloud.257 npm6MIT
- AlicenseAqualityBmaintenanceVersioned document vault system for MCP-compatible AI agents. Organizes reference knowledge (specs, contracts, rules) into per-project vaults with 36 MCP tools for inject, search, link, and version operations. Local SQLite backend. Works with Claude, Cursor, Codex, Hermes Agent. Free (3 vaults) / Pro ($9/mo).494Business Source 1.1