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 the server in HTTP mode (e.g. MODE=http npx agent-search-mcp). | |
| PROXY_URL | No | The explicit proxy URL used when USE_PROXY=true. | |
| USE_PROXY | No | Set to true to use PROXY_URL as an explicit proxy. | |
| EXA_API_KEY | No | Optional API key for the Exa Search provider (neural search). | |
| YDC_API_KEY | No | Optional API key for the You.com Search provider (commercial Web Search). | |
| OUTPUT_STYLE | No | Set to compact to reduce response tokens (compact mode keeps full detail for the first results and reduces later entries to source-preserving references). | |
| RERANK_TOP_K | No | Number of top results considered by optional semantic reranking. | |
| BOCHA_API_KEY | No | Optional API key for the Bocha Web Search provider (Chinese-first AI search). | |
| BRAVE_API_KEY | No | Optional API key for the Brave Search provider (commercial Web Search). | |
| ENABLED_TOOLS | No | Tool registration allowlist. | all |
| DENIED_ENGINES | No | Engine execution denylist; deny wins. | none |
| DISABLED_TOOLS | No | Tool registration denylist; deny wins. | none |
| SEMANTIC_DEDUP | No | Enable optional semantic deduplication (uses Python and Model2Vec). | |
| SERPER_API_KEY | No | Optional API key for the Serper Google Search provider (Google SERP search). | |
| SNIPPET_LENGTH | No | Controls snippet length in output to reduce response tokens. | |
| TAVILY_API_KEY | No | Optional API key for the Tavily Search provider (agent-oriented search). | |
| WIBY_PROXY_URL | No | Explicit proxy URL for the Wiby engine. Engine-specific single-proxy variables take precedence over their pool. | |
| ALLOWED_ENGINES | No | Engine execution allowlist. | all |
| ALLOWED_ORIGINS | No | Browser requests with an Origin header must match this value. | |
| DEDUP_THRESHOLD | No | Threshold used by optional semantic deduplication. | |
| HTTP_AUTH_TOKEN | No | 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 the Sogou engine. Engine-specific single-proxy variables take precedence over their 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 | Number of results kept with full detail; later entries are reduced to source-preserving references. | |
| MOJEEK_PROXY_URL | No | Explicit proxy URL for the Mojeek engine. Engine-specific single-proxy variables take precedence over their 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 the exact-result cache, in milliseconds. | |
| TENCENT_WSA_API_KEY | No | Optional API key for the Tencent Web Search API (official Chinese Web Search). | |
| DUCKDUCKGO_PROXY_URL | No | Explicit proxy URL for the DuckDuckGo engine. Engine-specific single-proxy variables take precedence over their pool. | |
| SEARCH_PROVIDER_MODE | No | Default routing policy: free_first, quality_escalation, paid_first, or free_only. The default free_first policy never spends a configured API credential; free_only blocks paid providers. | 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; caps query-relevant passages across the complete response. | 1200 |
| SEARCH_CACHE_DIRECTORY | No | Directory to persist the exact-result cache. The default exact-result cache stays in memory; setting this opts into local persistence. | |
| SEARCH_BUDGET_MAX_CALLS | No | Adapter-attempt budget. | 16 |
| SEARCH_CACHE_MAX_ENTRIES | No | Maximum number of entries in the exact-result cache. | |
| SEARCH_BUDGET_MAX_RESULTS | No | Admitted raw-result budget. | 100 |
| HTTP_ALLOW_UNAUTHENTICATED | No | Set to true to allow HTTP mode without HTTP_AUTH_TOKEN. | |
| SEARCH_BUDGET_MAX_ELAPSED_MS | No | End-to-end elapsed-time budget in milliseconds. | 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
ResponsivenessResponsive