agent-search-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MODE | No | Set to "http" to run in HTTP mode. Default is stdio mode. | |
| PROXY_URL | No | Explicit proxy URL used when USE_PROXY=true. | |
| USE_PROXY | No | Set to true together with PROXY_URL to use an explicit proxy. | |
| EXA_API_KEY | No | Optional API key for Exa Search, an optional neural Search engine. | |
| YDC_API_KEY | No | Optional API key for You.com Search, an optional commercial Web Search engine. | |
| OUTPUT_STYLE | No | Output style. Set to compact to reduce response tokens. | |
| RERANK_TOP_K | No | Top-K value for optional semantic reranking. | |
| BOCHA_API_KEY | No | Optional API key for Bocha Web Search, an optional Chinese-first AI Search engine. | |
| BRAVE_API_KEY | No | Optional API key for Brave Search, an optional commercial Web Search engine. | |
| ENABLED_TOOLS | No | Tool registration allowlist. Default is all tools enabled. | |
| DENIED_ENGINES | No | Engine execution denylist. Deny wins over allow. Default is none denied. | |
| DISABLED_TOOLS | No | Tool registration denylist. Deny wins over allow. Default is none disabled. | |
| SEMANTIC_DEDUP | No | Enable optional semantic deduplication (uses Python and Model2Vec). | |
| SERPER_API_KEY | No | Optional API key for Serper Google Search, an optional Google SERP Search engine. | |
| SNIPPET_LENGTH | No | Length of result snippets. | |
| TAVILY_API_KEY | No | Optional API key for Tavily Search, an optional agent-oriented Search engine. | |
| WIBY_PROXY_URL | No | Explicit proxy URL for Wiby. Takes precedence over the Wiby proxy pool. | |
| ALLOWED_ENGINES | No | Engine execution allowlist. Default is all engines allowed. | |
| ALLOWED_ORIGINS | No | Browser requests with an Origin header must match one of these allowed origins. | |
| DEDUP_THRESHOLD | No | Threshold for optional semantic deduplication. | |
| HTTP_AUTH_TOKEN | No | Authentication token for HTTP mode. Required in HTTP mode unless HTTP_ALLOW_UNAUTHENTICATED=true. | |
| SEMANTIC_RERANK | No | Enable optional semantic reranking (uses Python and Model2Vec). | |
| SOGOU_PROXY_URL | No | Explicit proxy URL for Sogou. Takes precedence over the Sogou proxy pool. | |
| WIBY_PROXY_URLS | No | User-owned proxy pool for Wiby as a JSON array of 2-16 HTTP(S) proxy URLs. | |
| MAX_FULL_RESULTS | No | Maximum number of full results before later entries are compacted. | |
| MOJEEK_PROXY_URL | No | Explicit proxy URL for Mojeek. Takes precedence over the Mojeek proxy pool. | |
| SOGOU_PROXY_URLS | No | User-owned proxy pool for Sogou as a JSON array of 2-16 HTTP(S) proxy URLs. | |
| MOJEEK_PROXY_URLS | No | User-owned proxy pool for Mojeek as a JSON array of 2-16 HTTP(S) proxy URLs. | |
| PAID_ENGINE_ORDER | No | Selects the first configured optional provider; not a quality claim. | brave,exa,tavily,youcom,tencent_wsa,bocha,serper |
| SEARCH_CACHE_TTL_MS | No | Time-to-live for exact-result cache entries, in milliseconds. | |
| TENCENT_WSA_API_KEY | No | Optional API key for the Tencent Web Search API, an optional official Chinese Web Search engine. | |
| DUCKDUCKGO_PROXY_URL | No | Explicit proxy URL for DuckDuckGo. Takes precedence over the DuckDuckGo proxy pool. | |
| SEARCH_PROVIDER_MODE | No | Default routing policy: free_first, quality_escalation, paid_first, or free_only. | free_first |
| DUCKDUCKGO_PROXY_URLS | No | User-owned proxy pool for DuckDuckGo as a JSON array of 2-16 HTTP(S) proxy URLs. | |
| EVIDENCE_BUDGET_CHARS | No | Evidence-character budget. | 1200 |
| SEARCH_CACHE_DIRECTORY | No | Directory for the exact-result cache. Setting this opts into local persistence; by default the cache stays in memory. | |
| SEARCH_BUDGET_MAX_CALLS | No | Adapter-attempt budget. | 16 |
| SEARCH_CACHE_MAX_ENTRIES | No | Maximum number of exact-result cache entries. | |
| SEARCH_BUDGET_MAX_RESULTS | No | Admitted raw-result budget. | 100 |
| HTTP_ALLOW_UNAUTHENTICATED | No | Set to true to allow HTTP requests without authentication. | |
| SEARCH_BUDGET_MAX_ELAPSED_MS | No | End-to-end elapsed-time budget. | 30000 |
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
ActivityActive
ResponsivenessNo issues