agent-herder
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CODEX_BIN | No | Path to Codex CLI binary | codex |
| CLAUDE_BIN | No | Path to Claude Code CLI binary | claude |
| ENABLE_CODEX | No | Enable Codex adapter | true |
| OPENCODE_URL | No | OpenCode server URL | http://127.0.0.1:4096 |
| ENABLE_CLAUDE | No | Enable Claude Code adapter | true |
| CODEX_DATA_DIR | No | Codex data directory | ~/.codex |
| ENABLE_OPENCODE | No | Enable OpenCode adapter | true |
| OPENCODE_SERVER_PASSWORD | No | Password for OpenCode server auth | |
| OPENCODE_SERVER_USERNAME | No | Username for OpenCode server auth | opencode |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_agentsA | List all coding agent sessions. Filter by harness, status, age (maxAge seconds), or folder (CWD prefix like ~/apps). Can show last message preview. |
| agent_infoB | Get detailed info about a specific session. Always shows model and last message. |
| send_messageA | Send a message to an agent. Modes: sync (wait), queue (fire-and-forget), steer (redirect). |
| stop_agentB | Stop / abort a running agent session. |
| respond_permissionB | Respond to a pending permission request (allow/deny). OpenCode and Claude SDK support this. |
| set_permissionsC | Set permissions for an agent. Claude/Codex set these at launch time. |
| resume_agentB | Resume a stopped agent session. Optionally provide a message. |
| summarize_sessionA | Summarize a session transcript using built-in gemma4 LLM. Returns structured summary (Task, Progress, Current State, Issues). Use quick=true for 1-3 sentences. |
| change_modelA | Change the AI model for a harness. For OpenCode: per-session or global. For Claude/Codex: updates default for future sessions. |
| list_modelsA | List available AI models for each harness. |
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/megamen32/agent-herder'
If you have feedback or need assistance with the MCP directory API, please join our Discord server