TubeTrace MCP
by ph20
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | Application bind address (in Docker 0.0.0.0:8000). | |
| PORT | No | Application bind port. | |
| APP_ENV | No | development / production (fail-closed). | |
| LOG_LEVEL | No | Logging level. | |
| ACME_EMAIL | No | E-mail for Let's Encrypt. | |
| LOG_FORMAT | No | JSON (default) or text; secrets are redacted. | |
| MCP_DOMAIN | No | Public hostname for Caddy and the Host check. Required in production (or use ALLOWED_HOSTS). | |
| ALLOWED_HOSTS | No | Extra Host values (comma-separated). Required in production if MCP_DOMAIN is not set. | |
| AUTH_DISABLED | No | true disables auth only in development; in production it is a startup error. | |
| PROXY_HEADERS | No | Trust X-Forwarded-* only from your own Caddy. | |
| ALLOWED_ORIGINS | No | Extra Origin values (comma-separated). CLI clients without an Origin pass; a foreign Origin is rejected (403), a foreign Host gets 421. | |
| CACHE_MAX_BYTES | No | Max cache bytes. | |
| YOUTUBE_API_KEY | No | Google key restricted to the YouTube Data API v3. Optional; without it search returns GOOGLE_API_NOT_CONFIGURED but transcripts keep working. | |
| MCP_TOKEN_SHA256 | No | SHA-256 hex digest(s) of the bearer token, comma-separated for rotation. Required in production. | |
| RATE_LIMIT_BURST | No | Rate limit burst. | |
| CACHE_MAX_ENTRIES | No | Max cache entries. | |
| MAX_RESPONSE_BYTES | No | Size of one MCP result page (default 200,000). | |
| FORWARDED_ALLOW_IPS | No | Trust X-Forwarded-* only from your own Caddy (compose assigns the static address 172.28.0.10). | |
| TOOL_TIMEOUT_SECONDS | No | Time budget of one call. | |
| TRANSCRIPT_MAX_BYTES | No | Max transcript bytes. | |
| UPSTREAM_MAX_RETRIES | No | Bounded retries with backoff/jitter. | |
| RATE_LIMIT_PER_MINUTE | No | Rate limit per minute. | |
| MAX_REQUEST_BODY_BYTES | No | Max HTTP request body bytes. | |
| TRANSCRIPT_MAX_SEGMENTS | No | Max transcript segments. | |
| SEARCH_CACHE_TTL_SECONDS | No | Search cache TTL (default 300). | |
| UPSTREAM_MAX_CONCURRENCY | No | Concurrent upstream request limit. | |
| GOOGLE_MAX_RESPONSE_BYTES | No | Max Google API response bytes. | |
| TRANSCRIPT_CACHE_TTL_SECONDS | No | Transcript cache TTL (default 3600). | |
| UPSTREAM_RETRY_BUDGET_SECONDS | No | Retry budget in seconds. | |
| UPSTREAM_QUEUE_TIMEOUT_SECONDS | No | Queue timeout for upstream requests. |
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 | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues