bearer-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | Listen address (Cloud Run: auto 0.0.0.0) | 127.0.0.1 |
| PORT | No | HTTP listen port | 3000 |
| MCP_TOKEN_FILE | No | Path to JSON file with token definitions | |
| MCP_CORS_ORIGIN | No | CORS origin for browser access | * |
| MCP_REQUIRE_AUTH | No | Enforce bearer token auth on HTTP | true |
| MCP_BEARER_TOKENS | No | Comma-separated valid bearer tokens | |
| MCP_LOG_BODY_LIMIT | No | Max chars for request/response body logging | 4000 |
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
} |
| logging | {} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| echoA | Echoes back the text you send. Useful as a connectivity and authentication check. |
| search_projectsA | Search for projects by name, language, status, or tags. Returns paginated results with metadata. |
| get_projectA | Get full details for a single project by its ID. |
| create_projectA | Create a new project in the platform. Returns the created project with its assigned ID. |
| deploy_serviceA | Triggers a deployment for a project to a target environment. Simulates the deployment pipeline and returns a deployment ID for tracking. |
| list_api_keysA | List all API keys for a project. Keys are returned with masked values — the full key is only shown at creation time. |
| rotate_api_keyA | Rotate (regenerate) an existing API key. The old key is immediately invalidated and a new key value is returned. This is the only time the full key is visible. |
| get_metricsA | Get usage and performance metrics for a project over the last 24 hours. Returns hourly data points with request counts, errors, and latency percentiles. |
| search_logsA | Full-text search across application log entries. Filter by project, severity level, or free-text query. Returns the most recent matching entries. |
| run_diagnosticA | Run a comprehensive health diagnostic on a project. Checks connectivity, recent errors, configuration validity, and resource utilization. Returns structured results. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| debug_deployment | Produces a prompt asking the model to diagnose and suggest fixes for a failed deployment. |
| write_api_docs | Asks the model to generate API documentation for an endpoint in a given language/framework. |
| review_config | Asks the model to review a configuration file (YAML/JSON/TOML) for correctness, security issues, and best practices. |
| incident_postmortem | Asks the model to draft a blameless postmortem for a service incident. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| server-config | Server configuration, version info, and feature flags. |
| api-reference | Markdown API reference for the mock developer platform. |
| system-status | Live system status including services, regions, and active incidents. |
| stellar-api | stellar-api — typescript / active |
| nebula-web | nebula-web — typescript / active |
| quantum-worker | quantum-worker — python / active |
| horizon-mobile | horizon-mobile — typescript / active |
| aurora-ml | aurora-ml — python / active |
| cipher-auth | cipher-auth — go / active |
| cascade-events | cascade-events — rust / active |
| prism-analytics | prism-analytics — typescript / inactive |
| echo-notifications | echo-notifications — go / active |
| vault-secrets | vault-secrets — rust / active |
| falcon-cdn | falcon-cdn — go / active |
| mercury-ingest | mercury-ingest — python / active |
| phoenix-recovery | phoenix-recovery — go / active |
| lighthouse-monitor | lighthouse-monitor — typescript / active |
| zenith-scheduler | zenith-scheduler — python / inactive |
| titan-db | titan-db — rust / active |
| orion-search | orion-search — go / active |
| glacier-storage | glacier-storage — python / archived |
| ember-chat | ember-chat — typescript / active |
| nova-i18n | nova-i18n — typescript / active |
| Ada Lovelace | Ada Lovelace (admin) — ada@example.com |
| Alan Turing | Alan Turing (developer) — alan@example.com |
| Grace Hopper | Grace Hopper (admin) — grace@example.com |
| Linus Torvalds | Linus Torvalds (developer) — linus@example.com |
| Margaret Hamilton | Margaret Hamilton (developer) — margaret@example.com |
TDQS
Scored across 10 tools
Each tool targets a distinct resource and action: projects (create, get, search), deployments, API keys (list, rotate), metrics, logs, diagnostics, and connectivity. There is no overlap or ambiguity between tool purposes.
Most tools follow a clear verb_noun snake_case pattern (create_project, search_logs, rotate_api_key). The only deviation is 'echo', which lacks a noun object, but this is a minor utility and does not undermine the overall pattern.
With 10 tools, the server is well-scoped for a platform management API. Each tool covers a distinct aspect of project and deployment management, observability, and diagnostics, without unnecessary bloat.
The server covers project creation, retrieval, search, and deployment, but lacks update/delete operations for projects and API key creation/deletion. Deployment status tracking is also missing. These are notable gaps that agents may need to work around.