agentflow-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP port used when transport is 'http-stream'. | 8080 |
| MCP_TRANSPORT | No | Transport mode for the MCP server: 'stdio' (default) or 'http-stream'. | stdio |
| GRAYLOG_SOURCE | No | Source name for Graylog messages. | agentflow-mcp |
| GRAYLOG_GELF_URL | No | Graylog GELF HTTP input URL (e.g. http://graylog:12201/gelf). Enables Graylog logging when set. | |
| BRANDFETCH_API_KEY | No | Bearer token for Brandfetch Brand Context API. Required by brand_context_lookup; when missing, returns cached or graceful unavailable responses for uncached domains. | |
| LOGO_DEV_SECRET_KEY | No | Bearer token for logo.dev Brand API. Required by brand_context_lookup; when missing, returns cached or graceful unavailable responses for uncached domains. | |
| LOGO_DEV_PUBLISHABLE_KEY | No | Publishable key for logo.dev CDN URLs. Required by brand_context_lookup; when missing, returns cached or graceful unavailable responses for uncached domains. |
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 | {} |
| logging | {} |
| completions | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| arch_pattern_lookupA | Match an enterprise ask (industry, data stack, cloud, constraints) to a curated reference architecture pattern with components, data zones, integration notes, confidence, and diagram-ready data. |
| tool_selection_lookupA | Recommend a data platform based on use case, data stack, constraints (HIPAA, PII, data residency, SSO/SAML), and latency needs — with cloud fit, reasoning, and alternatives. |
| risk_policy_lookupA | Return required controls, risk flags, and human-in-the-loop triggers for an architecture based on industry, data classification (PHI, PII, regulated financial data), region, deployment model, and governance constraints. |
| brand_context_lookupA | Retrieve company brand context (name, description, tags, positioning, brand voice/style, logo URL) for a resolved domain, from Brandfetch plus logo.dev. Serves cached data when the sources are unavailable. Resolve partial company names to a domain before calling. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool targets a distinct outcome: architecture pattern, brand info, platform recommendation, and risk controls. There is some conceptual overlap between architecture patterns and tool/risk recommendations, but the descriptions make their outputs clear enough to avoid major misselection.
All tool names follow the same clear `entity_lookup` pattern in lowercase snake_case: arch_pattern_lookup, brand_context_lookup, tool_selection_lookup, risk_policy_lookup. This makes the server feel uniform and predictable.
With only 4 focused lookup tools, the server is tightly scoped and does not introduce redundancy. Each tool serves a distinct functional need, making this an appropriate small toolset.
The server covers the major lookup categories it appears designed for: architecture, brand, platform, and policy. It is slightly limited by the lack of any listing or browsing endpoint for available patterns/platforms, but for a retrieval-oriented tool set the core coverage is strong.