llm-oracle
Pulls fresh LLM pricing and availability from a continuously updated catalog so your agent can route requests to the cheapest or most appropriate model at runtime. Exposes five MCP tools: list_models for browsing with optional filters, get_model for full details on a specific model, find_cheapest to rank options by estimated cost given token counts, compare_models for side-by-side analysis, and check_availability for current status. Every price claim links back to the provider's official docs. Covers Anthropic, OpenAI, Google, DeepSeek, and Mistral with daily price updates. Reach for this when you're building multi-model routing logic and don't want to maintain your own pricing table or scrape provider pages yourself.
- tools
- 5
- transport
- STDIO
- env vars
- 2
- last updated
- May 30, 2026
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
list_modelsList models, optionally filtered by provider or capability.
List models, optionally filtered by provider or capability.
No parameter schema in public metadata yet.
get_modelFull record for one model.
Full record for one model.
No parameter schema in public metadata yet.
find_cheapestRanked by estimated cost for given input and output tokens.
Ranked by estimated cost for given input and output tokens.
No parameter schema in public metadata yet.
compare_modelsSide-by-side comparison of models.
Side-by-side comparison of models.
No parameter schema in public metadata yet.
check_availabilityCurrent status of a model with cited source.
Current status of a model with cited source.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
LLM_ORACLE_URLOverride the remote catalog URL (default https://oracle.weiseer.com/catalog.json)
LLM_ORACLE_LOCAL_ONLYSet to any value to skip remote fetch and use bundled catalog only
Readme
llm-oracle
Continuously-updated catalog + query API for LLM provider availability and pricing.
Built by weiseer.
What it does
Given a question like "for this prompt of N input tokens plus M expected output tokens, which currently-available model offers the lowest cost?" the oracle answers in milliseconds, with the source URL it used for the pricing claim.
Use it as:
- an MCP server for AI agents that need to make routing decisions at inference time
- an HTTP JSON API for any tool that wants up-to-date LLM pricing/availability
- a raw
catalog.jsonyou can audit, vendor, or contribute fixes to
Why
LLM pricing changes monthly. Every multi-model app rebuilds the same lookup table. We maintain it so you don't.
- Cited: every pricing row links to the provider's official documentation
- Versioned:
as_oftimestamp on every response so you know how fresh the data is - Open: catalog is public JSON, MIT licensed; client/server code is Apache-2.0
- Cross-checked: source data verified against the open-source LiteLLM price file where overlap exists
Coverage (v0)
Details
- Repository
- github.com/weiseer/llm-oracle
- Category
- AI & LLM Tools
- Package
@weiseer/llm-oracle-mcp- Transport
- STDIO
- Registry
- MCP registry, active
More from weiseer
Related AI & LLM Tools MCP servers
View all
Agent-Native Analyticsbuilderio/agent-nativeAgent-Native Amplitude/Mixpanel - connect data sources, prompt for charts7.6KstarsAgent-Native Dispatchbuilderio/agent-nativeCentral Slack/Telegram router with jobs, memory, approvals, and A2A delegation7.6Kstars
GPT Researcherassafelovic/gptr-mcpMCP server for enabling LLM applications to perform deep research via the MCP protocol346stars
RAG Documentationhannesrudolph/mcp-ragdocsAn MCP server implementation that provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their resp261stars
Agent Commsexadev/agent-commsCross-harness communication mesh for LLM agents — rooms, DMs, presence, and visibility over TCP37stars
Mnemoverse Memorymnemoverse/mcp-memory-serverHosted agent memory that learns from outcomes, with shared rooms. No key: mcp.mnemoverse.com/mcp28stars