WisdomAgent
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WA_HOST | No | Host interface to bind the API server to. | 0.0.0.0 |
| WA_PORT | No | Port for the API server. | 8000 |
| WA_RRF_K | No | Reciprocal rank fusion constant k. | 60 |
| WA_BM25_B | No | BM25 b parameter. | 0.75 |
| WA_BM25_K1 | No | BM25 K1 parameter. | 1.2 |
| WA_LOG_JSON | No | Emit structured JSON logs if 'true', otherwise pretty-print. | true |
| WA_LLM_MODEL | No | Model name for LLM calls. | gpt-4o-mini |
| WA_LOG_LEVEL | No | Logging level (DEBUG, INFO, WARNING, ERROR). | INFO |
| WA_MAX_TOP_K | No | Maximum allowed top-K (requests are clamped). | 100 |
| WA_REDIS_URL | No | Redis connection URL. Blank disables caching. | |
| WA_MAX_CLAIMS | No | Maximum number of claims in an answer. | 12 |
| WA_NGRAM_SIZE | No | Character n-gram size for tokenization. | 4 |
| WA_ENVIRONMENT | No | Environment label for logs and metrics. | local |
| WA_KAFKA_TOPIC | No | Kafka topic for domain events. | wisdomagent.events |
| WA_LLM_API_KEY | No | API key for the LLM provider. | |
| WA_MIN_SUPPORT | No | Minimum support threshold for grounding. | 0.6 |
| WA_DATABASE_DSN | No | Postgres connection string. Blank uses in-memory repository. | |
| WA_LLM_BASE_URL | No | Base URL for OpenAI-compatible LLM API. Blank uses deterministic offline path. | |
| WA_DEFAULT_TOP_K | No | Default top-K for retrieval. | 10 |
| WA_EMBEDDING_DIM | No | Embedding dimension for hashed vectors. | 128 |
| WA_KAFKA_BROKERS | No | Comma-separated Kafka broker list. Blank uses in-process publisher. | |
| WA_OTLP_ENDPOINT | No | OTLP endpoint for tracing. Blank disables tracing. | |
| WA_TENANT_SHARDS | No | Number of hash shards for tenant partitioning. | 4 |
| WA_BOOTSTRAP_DEMO | No | If set, seeds the corpus with synthetic demo data. | |
| WA_DEFAULT_TENANT | No | Tenant used when x-tenant-id header is absent. | default |
| WA_EMBEDDING_SEED | No | Seed for deterministic hashed embeddings. | 1337 |
| WA_EVIDENCE_LIMIT | No | Maximum number of evidence documents considered. | 8 |
| WA_AGENT_MAX_STEPS | No | Maximum number of agent steps. | 8 |
| WA_FUSION_STRATEGY | No | Fusion strategy: 'rrf' or 'weighted'. | rrf |
| WA_TIMEOUT_SECONDS | No | Timeout for outbound I/O calls. | 5.0 |
| WA_AGENT_MAX_TOKENS | No | Maximum token budget for agent. | 8000 |
| WA_MIN_GROUNDEDNESS | No | Minimum groundedness score for acceptance. | 0.7 |
| WA_AGENT_MAX_REPAIRS | No | Maximum number of repair attempts. | 1 |
| WA_CACHE_TTL_SECONDS | No | TTL for cached answers/aggregates. | 300 |
| WA_RETRY_MAX_ATTEMPTS | No | Maximum retry attempts for resilient calls. | 3 |
| WA_RATE_LIMIT_CAPACITY | No | Rate limiter capacity (burst). | 200 |
| WA_WORKER_METRICS_PORT | No | Port for the worker's metrics endpoint. | 8001 |
| WA_BREAKER_OPEN_SECONDS | No | How long the circuit breaker stays open. | 10.0 |
| WA_CANDIDATE_MULTIPLIER | No | Retrieval depth multiplier before reranking. | 4 |
| WA_MCP_MAX_OUTPUT_CHARS | No | Maximum characters in MCP tool output. | 20000 |
| WA_PARTITION_SPAN_MONTHS | No | Width of range partitions in months. | 1 |
| WA_MIN_EVIDENCE_RELEVANCE | No | Evidence relevance floor below which the system refuses. | 0.25 |
| WA_BULKHEAD_MAX_CONCURRENT | No | Maximum concurrent calls per dependency. | 32 |
| WA_AGENT_MAX_CALLS_PER_TOOL | No | Maximum number of calls per tool per run. | 3 |
| WA_MCP_CALL_TIMEOUT_SECONDS | No | Timeout for MCP tool calls. | 10.0 |
| WA_MONITOR_INTERVAL_SECONDS | No | Monitor worker sweep interval. | 300.0 |
| WA_BREAKER_FAILURE_THRESHOLD | No | Number of failures to open the circuit breaker. | 5 |
| WA_AGENT_MAX_WALL_CLOCK_SECONDS | No | Maximum wall clock time for a run. | 30.0 |
| WA_RATE_LIMIT_REFILL_PER_SECOND | No | Rate limiter refill rate per second. | 100.0 |
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/ABHIJEET-MUNESHWAR/WisdomAgent'
If you have feedback or need assistance with the MCP directory API, please join our Discord server