swarm-search
by jumpleGo
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SWARM_ROUND2 | No | Default round-2 mode. Default: gaps | |
| SWARM_ROUNDS | No | Default rounds. Default: 1 | |
| SWARM_WORKERS | No | Fixed default worker count. Default: unset = auto | |
| GEMINI_API_KEY | No | API key for Gemini providers (gemini-cli and google) | |
| GOOGLE_API_KEY | No | API key for Google provider | |
| OPENAI_API_KEY | No | API key for OpenAI provider | |
| SWARM_PROVIDER | No | Default provider spec. Default: auto | |
| SWARM_AGY_MODEL | No | Per-provider default model for Antigravity | |
| SWARM_HTTP_TOKEN | No | Bearer token for mcp --http (required when binding a non-loopback host) | |
| SWARM_TIMEOUT_MS | No | Per-call timeout in milliseconds. Default: 180000 | |
| ANTHROPIC_API_KEY | No | API key for Anthropic provider | |
| SWARM_CODEX_MODEL | No | Per-provider default model for Codex | |
| SWARM_SHARD_CHARS | No | Max characters per files-mode shard. Default: 60000 | |
| OPENROUTER_API_KEY | No | API key for OpenRouter provider | |
| SWARM_CLAUDE_MODEL | No | Per-provider default model for Claude | |
| SWARM_GEMINI_MODEL | No | Per-provider default model for Gemini CLI | |
| SWARM_GOOGLE_MODEL | No | Per-provider default model for Google | |
| SWARM_OPENAI_MODEL | No | Per-provider default model for OpenAI | |
| SWARM_ANTHROPIC_MODEL | No | Per-provider default model for Anthropic | |
| SWARM_MAX_AUTO_WORKERS | No | Upper bound for auto sizing. Default: 8 | |
| SWARM_OPENROUTER_MODEL | No | Per-provider default model for OpenRouter | |
| SWARM_HTTP_ALLOWED_ORIGINS | No | Comma-separated browser origins allowed besides localhost (mcp --http) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jumpleGo/swarm-search'
If you have feedback or need assistance with the MCP directory API, please join our Discord server