mcp-foresea
by pareelamre
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| REDIS_URL | No | Memorystore/Redis URL for shared cache and rate limits. | |
| NEWSAPI_KEY | No | NewsAPI key for news evidence. | |
| SEARXNG_URL | No | URL of a self-hosted SearXNG instance for web search evidence. | |
| MODEL_DEVICE | No | Device for model inference (cpu or cuda). | cpu |
| BRAVE_API_KEY | No | Brave API key for web search evidence. | |
| CUSTOM_DOMAIN | No | Custom domain for redirects. | foresea.ink |
| SERPER_API_KEY | No | Serper API key for web search evidence. | |
| SESSION_SECRET | No | Long random string used to sign browser session JWTs. | |
| TAVILY_API_KEY | No | Tavily API key for web search evidence. | |
| FORESEA_API_KEY | No | Optional API key for private deployment auth; forwarded as X-API-Key. | |
| LOCAL_CACHE_MAX | No | Max entries in the in-memory fallback cache. | 1024 |
| GITHUB_CLIENT_ID | No | GitHub OAuth client ID. | |
| GOOGLE_CLIENT_ID | No | Google OAuth web client ID. | |
| SCADS_AI_API_KEY | Yes | API key for the hosted model endpoint used by the MCP server. | |
| EXTRACT_CACHE_TTL | No | Cache TTL (s) for /extract URL fetches. | 3600 |
| PREDICT_CACHE_TTL | No | Cache TTL (s) for non-personalised /predict responses. | 600 |
| EVIDENCE_CACHE_TTL | No | Cache TTL (s) for evidence retrieval. | 900 |
| GITHUB_CLIENT_SECRET | No | GitHub OAuth client secret. |
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/pareelamre/analyzing-llm-rationale'
If you have feedback or need assistance with the MCP directory API, please join our Discord server