Rhumb
Server Details
Which AI model to call on the providers you have: model id, price and reason.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 9 tools
The three cluster heads (resolve, plan, platform/stack) are separated by explicit routing cues — plan vs resolve is called out in both descriptions, and get_model vs list_models vs list_purposes differ by cardinality and resource. The remaining overlap is between the free lookup helpers (get_vocabulary, list_goals, list_purposes), which all serve the same 'fetch names before calling' role but return different axes, so confusion is possible but recoverable.
The five lookup tools use a clean verb_noun pattern (get_model, get_vocabulary, list_models, list_goals, list_purposes). The four workhorse tools break it with bare terms — plan, platform, resolve, stack — and 'platform' is a noun where everything else is verb-first.
Nine tools for a model/platform/stack advisor is well-scoped: three answer engines (resolve, platform, stack), one parser (plan), and five cheap lookups that feed them. No tool looks redundant or padded.
The surface covers the full path from user words to a decided model, platform and stack, including failure reporting (no_candidate, unknown_systems) and vocabulary discovery. Gaps are minor: no provider-level detail view (a provider's full catalog and rate limits) and no direct cost-estimate tool for a stated workload, both of which agents must reconstruct from list_models/get_model output.
Available Tools
9 toolsget_modelGet one modelARead-onlyInspect
One model by id (vendor/model, e.g. anthropic/claude-sonnet-4.5): every provider's offering with its price history, capabilities, limits and dates, and the model's quality scores. Counts as one call.
Inputs: id (required), at, provider.
get_vocabularyGet the vocabularyARead-onlyInspect
Every name the other tools accept: tasks, capabilities and their levels, providers, origin groups, budgets and team strategies. Free.
Inputs: no named parameters.
list_goalsList the goalsARead-onlyInspect
The goals an answer depends on (cost, depth, where a model's maker is based, where data may stay, languages, the kind of data, the accounts already held), each with one question to ask the user, the options to offer and the parameters each answer is sent as, and the rules for asking. Call it once when planning an app. Free.
Inputs: no named parameters.
list_modelsList modelsARead-onlyInspect
The catalog's models with each provider's offering, price, capabilities and quality scores, filtered by task, providers and needs. Returns 20 models unless limit says otherwise; page with offset. Counts as one call.
Inputs: task, limit, needs, offset, +3 more.
list_purposesList purposesARead-onlyInspect
The purpose presets resolve accepts: named jobs such as reading receipts or a coding agent, each with the task, needs and budget it stands for. Free.
Inputs: no named parameters.
planPlan from a descriptionARead-onlyInspect
Reads a description of the work (a prompt, tags, attachment types and sizes) into a need, then resolves it as resolve does. Use resolve when you can state the task or purpose yourself; use this when you only have the user's words. Counts as more than one call. The answer depends on these goals; have the ones that matter in hand from the plan, the repository or the user before calling: cost (optimize, max_price, budget, calls_per_user_month); depth (optimize, quality_margin, min_quality, budget, shape, needs); maker_origin (origin, origin_strict); data_region (regions); languages (languages); data_kind (needs); accounts (providers). Send them as strings in constraints; only providers and shape go at the top level.
Inputs: providers (required), tags, shape, device, +4 more.
platformChoose where an app's agent runsARead-onlyInspect
Where an app's agent runs: give requires (baa, gpu, private_network, edge, long_running, websockets, scheduled_jobs, large_uploads) with longest_turn_seconds and largest_upload_mb where they apply, and the goals you have. The answer is major (a platform is warranted: a requirement no curated runtime meets, a model provider it hosts, or an account held; name its system in a stack call next) or generic (any host meeting host_must will do, with the runtimes that meet it priced for a stated job). Every host ruled out comes with its own page's words; a host whose pages do not state a fact is neither ruled in nor out. A choice is made only when the rules settle it; otherwise it is the user's. Counts as one call. The answer depends on these goals; have the ones that matter in hand from the plan, the repository or the user before calling: users_in (users_in); data_region (data_region); data_kind (data_kind); scale (scale); accounts (accounts, providers); clients (clients). On platform, a goal is sent by its own name (data_kind, data_region, users_in, scale, clients, accounts) with the values that call lists, and the model providers as providers; needs, regions and infra.vendors are not its parameters.
Inputs: scale, clients, accounts, requires, +6 more.
resolveResolve a modelARead-onlyInspect
Which model to call for a need, on the providers the user has accounts with: the provider's own model id, its price, capabilities and the reason. Give providers and a task or a purpose; add needs, budget, origin and other constraints to narrow it. shape asks for a team or an escalation ladder instead of one model. Counts as one call. An answer of no_candidate names what ruled every model out and the nearest miss. The answer depends on these goals; have the ones that matter in hand from the plan, the repository or the user before calling: cost (optimize, max_price, budget, calls_per_user_month); depth (optimize, quality_margin, min_quality, budget, shape, needs); maker_origin (origin, origin_strict); data_region (regions); languages (languages); data_kind (needs); accounts (providers). Send them as query parameters.
Inputs: providers (required), task, hours, needs, +41 more.
stackChoose a stack for an agentARead-onlyInspect
For an agent that has to work with named systems (Linear, GitHub, Postgres…): what to connect for each, and which model to call. Give systems, target (local or cloud) and the harness the agent runs in; add model.providers to get a model too. Each system's choice is its owner's own MCP server or command-line tool, or none, picked by fixed rules from public records and not reviewed; warnings say what to read first, and config.mcp_json is a config to start from, with placeholders for every value the user supplies. A name that matches no system comes back in unknown_systems. Counts as one call. The answer depends on these goals; have the ones that matter in hand from the plan, the repository or the user before calling: cost (optimize, max_price, budget, calls_per_user_month); maker_origin (origin, origin_strict); users_in (users_in); data_kind (needs); scale (scale); accounts (providers, infra.vendors); clients (clients). On stack, the app's goals go by their own names at the top (data_kind, users_in, scale, clients), a model's parameters in model.constraints and providers in model.providers; infrastructure vendors are infra.vendors. The stack's own top-level needs are what the agent does (web_search, web_reading, browser), never a model's.
Inputs: target (required), systems (required), infra, model, +11 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Live prices, rankings, licences and privacy of AI models: best model per task, costs, alternatives.
Sourced AI-model pricing and capability data — compare and route to the cheapest capable model.
AI model routing on your own vendor keys: pick the best model per prompt, or route and run it.
LLM provider intelligence: recommendations, pricing, and status
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables selecting the best AI model and reasoning effort for any task by analyzing task requirements and live pricing, balancing intelligence, speed, and cost. Provides model recommendations, comparisons, and routing status through MCP tools.26 npm3MIT
- FlicenseNot gradedqualityDmaintenanceAutomatically routes queries to the most suitable AI model based on task type, cost constraints, and performance needs, supporting multiple providers and customizable priorities.-
- AlicenseAqualityDmaintenanceEnables AI agents to discover, compare, and select the best AI models across multiple providers based on pricing, performance, and capabilities, with real-time cost estimation and benchmarking.91,281 npm1MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to compare costs, performance, and quality across 150+ models from 26 LLM providers, estimate or predict workload spend, route tasks to cost-effective models, and track actual recorded usage. Prices are cross-checked against a live external registry so drifted figures are flagged rather than silently served.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.