leftbrain
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATABASE_URL | No | Database URL for the key store; used if LEFTBRAIN_KEYS_URL is not set. | |
| LEFTBRAIN_DEBUG | No | Set to '1' to include a trace field in error responses. | |
| GITHUB_CLIENT_ID | No | GitHub OAuth client ID for the dashboard login. | |
| LEFTBRAIN_SECRET | No | Cookie signing secret (32+ random chars). Required for OAuth and for revealing keys in the dashboard. | |
| LEFTBRAIN_API_KEY | No | Secret API key used to protect the HTTP MCP server. | |
| LEFTBRAIN_KEYS_DB | No | Path to the SQLite database for the per-user key store. | |
| LEFTBRAIN_BASE_URL | No | Public base URL of the server, e.g. https://leftbrain.idlesync.in, used for the OAuth callback. Required for OAuth. | |
| LEFTBRAIN_KEYS_URL | No | Postgres DSN for the per-user key store. | |
| GITHUB_CLIENT_SECRET | No | GitHub OAuth client secret for the dashboard login. | |
| LEFTBRAIN_FILE_ROOTS | No | Allowed file paths for the file tools; access is limited to these roots. | |
| LEFTBRAIN_DEFAULT_RPM | No | Default requests per minute limit for new keys. | 60 |
| LEFTBRAIN_OPEN_SIGNUP | No | Set to '1' to allow anonymous signup. | |
| LEFTBRAIN_MAX_INFLIGHT | No | Concurrent workers. Default: CPU count. | |
| LEFTBRAIN_FEEDBACK_REPO | No | Repository for feedback issues, e.g. 'owner/repo'. | |
| LEFTBRAIN_QUEUE_TIMEOUT | No | How long a call waits for a free worker before returning busy. | 5 |
| LEFTBRAIN_FEEDBACK_TOKEN | No | Token for filing feedback issues; together with LEFTBRAIN_FEEDBACK_REPO enables /feedback. | |
| LEFTBRAIN_SERVE_EXTERNAL | No | Set to '0' to disable the network tools (weather, fx_rate, geo, url_check) in the server. | 1 |
| LEFTBRAIN_COMPUTE_TIMEOUT | No | Wall-clock seconds before the worker is terminated. | 15 |
| LEFTBRAIN_WORKER_MAX_TASKS | No | Calls before a worker is recycled (bounds SymPy's caches). | 200 |
| LEFTBRAIN_COMPUTE_ISOLATION | No | Set to '0' to run in-process (the library default). | 1 |
| LEFTBRAIN_WORKER_TERM_GRACE | No | SIGTERM to SIGKILL grace; a C loop never runs a handler. | 0.5 |
| LEFTBRAIN_MAX_RESPONSE_BYTES | No | Maximum size of a successful response. | 262144 |
| LEFTBRAIN_TRUSTED_PROXY_HOPS | No | Number of proxies appending to X-Forwarded-For. | 1 |
| LEFTBRAIN_WORKER_CPU_SECONDS | No | RLIMIT_CPU in the child, the kernel's backstop. Default: timeout + 2. | |
| LEFTBRAIN_DEFAULT_DAILY_QUOTA | No | Default daily quota for new keys. | 1000 |
| LEFTBRAIN_WORKER_MEMORY_BYTES | No | RLIMIT_AS in the child. | 1500000000 |
| LEFTBRAIN_SIGNUPS_PER_IP_PER_DAY | No | Maximum signups per IP per day. | 3 |
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/Lazy-Coder-03/leftbrain'
If you have feedback or need assistance with the MCP directory API, please join our Discord server