opengrok-go-mcp
by rokasklive
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEBUG | No | Set to '1' to log HTTP requests to stderr | |
| OPENGROK_MCP_LISTEN | No | HTTP listen address | |
| OPENGROK_MCP_BASE_URL | Yes | OpenGrok API base URL ending in /api/v1 | |
| OPENGROK_MCP_PROJECTS | No | Comma-separated allowlist of projects | |
| OPENGROK_MCP_API_TOKEN | No | Auth token for OpenGrok, value format: 'Bearer <token>' or 'Basic <credentials>' | |
| OPENGROK_MCP_CACHE_TTL | No | Cache entry lifetime | |
| OPENGROK_MCP_TRANSPORT | No | Transport: stdio or http | |
| OPENGROK_MCP_PROBE_FILE | No | project/path for file-read capability probe | |
| OPENGROK_MCP_TOOL_SURFACE | No | Tool surface: full, compact, gateway | |
| OPENGROK_MCP_WEB_BASE_URL | No | Web UI base for citations and raw-file fallback | |
| OPENGROK_MCP_AGENT_PROFILE | No | Agent profile: economy or rich | |
| OPENGROK_MCP_CACHE_ENABLED | No | In-process response cache | |
| OPENGROK_MCP_CONTEXT_AFTER | No | Expansion window lines after | |
| OPENGROK_MCP_CURSOR_SECRET | No | HMAC secret for signed pagination cursors | |
| OPENGROK_MCP_CACHE_MAX_SIZE | No | Max cache entries | |
| OPENGROK_MCP_CONTEXT_BEFORE | No | Expansion window lines before | |
| OPENGROK_MCP_MEMORY_ENABLED | No | Process-scoped memory tools on full surface only | |
| OPENGROK_MCP_DEFAULT_PROJECT | No | Implicit project when one is omitted; auto-set when exactly one project discovered | |
| OPENGROK_MCP_PROJECT_REQUIRED | No | Require project on tool calls (default true) | |
| OPENGROK_MCP_RETRY_BASE_DELAY | No | Retry backoff base | |
| OPENGROK_MCP_MAX_EXPANDED_FILES | No | Max files fetched during expansion | |
| OPENGROK_MCP_RETRY_MAX_ATTEMPTS | No | Retries for transient errors | |
| OPENGROK_MCP_AUTO_EXPAND_CONTEXT | No | Auto-expand context around search hits | |
| OPENGROK_MCP_MAX_EXPANDED_RESULTS | No | Max results to expand | |
| OPENGROK_MCP_DISABLE_PROJECT_SCRAPE | No | Skip web-UI scrape when /projects/indexed fails | |
| OPENGROK_MCP_INSECURE_SKIP_TLS_VERIFY | No | Skip TLS verification for trusted internal hosts | |
| OPENGROK_MCP_CONTEXT_FETCH_CONCURRENCY | No | Parallel fetches during expansion |
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/rokasklive/opengrok-go-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server