MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
LLM Pricing is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
100/100
trust score
7
downloads a day
local
or remote
1k
downloads in 30d
What it does
Real-time, drift-verified LLM pricing across 26 providers with cost+quality model routing.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user llm-pricing-mcp '--' npx -y llm-pricing-mcp
# 2 — ask your agent for something these tools do
# Pricing, Performance, Telemetry and 33 more
LLM Pricing costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
SKAll 1 server
skakumanu1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user llm-pricing-mcp '--' npx -y llm-pricing-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Or connect to its publisher’s address
Its publisher also runs it at https://llm-pricing-api.fly.dev/mcp: nothing to start on your machine, and this marketplace is not in the path.
claude mcp add --scope user --transport http llm-pricing-mcp https://llm-pricing-api.fly.dev/mcpFree on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take LLM_PRICING_MCP_URL (Upstream MCP endpoint to bridge to. Defaults to the hosted server; set to point at a self-hosted instance.), LLM_PRICING_MCP_TIMEOUT_MS (Per-request timeout to the upstream server, in milliseconds.), LLM_PRICING_API_KEY (Optional service API key (POST /billing/signup), sent as x-api-key. Only the usage and budget tools need it; they then act on your own org.) if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
36 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Live LLM model pricing data across 26 providers (150+ models). Supports filtering by provider and capability.
No parameter schema on file.
Quality scores, benchmark data, and use-case routing recommendations.
No parameter schema on file.
API usage metrics, endpoint adoption stats, and per-org cost savings tracking.
No parameter schema on file.
Customer sign-up, Stripe checkout, subscription portal, and account dashboard.
No parameter schema on file.
Liveness, readiness, and detailed health check endpoints for orchestrators.
No parameter schema on file.
Deployment metadata, API version info, and graceful shutdown control.
No parameter schema on file.
Internal admin endpoints — aggregate stats, rate-limit state, and customer list.
No parameter schema on file.
Get current pricing for all LLM models from all providers
No parameter schema on file.
Estimate the cost of using a specific LLM model
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model_name | string | yes | Name of the LLM model (e.g., 'gpt-4', 'claude-3-opus') |
| input_tokens | integer | yes | Number of input tokens |
| output_tokens | integer | yes | Number of output tokens |
Compare costs for multiple LLM models
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model_names | array | yes | List of model names to compare |
| input_tokens | integer | yes | Number of input tokens |
| output_tokens | integer | yes | Number of output tokens |
Get performance metrics (throughput, latency, context window) for models
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | no | Optional provider filter (e.g., 'openai', 'anthropic') |
| include_cost | boolean | no | Include cost metrics in response (default: true) |
Get recommended use cases and strengths for LLM models
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | no | Optional provider filter |
Get MCP server telemetry and usage statistics including tool usage, response times, and error rates
| Parameter | Type | Required | Notes |
|---|---|---|---|
| include_details | boolean | no | Include detailed statistics (default: true) |
| limit | integer | no | Maximum items per category (default: 10, max: 50) |
Query historical pricing snapshots recorded over time. Use this to look up past prices for a model or provider, or to see how prices have changed over a given number of days.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model_name | string | no | Filter by model name (e.g. 'gpt-4o'). Omit for all models. |
| provider | string | no | Filter by provider (e.g. 'openai'). Omit for all providers. |
| days | integer | no | Look-back window in days (default: 30, max: 365) |
| limit | integer | no | Maximum number of snapshot rows to return (default: 50, max: 500) |
Find models whose prices changed the most over a given period. Returns models sorted by absolute percentage price change with a direction label ('increased', 'decreased', or 'unchanged'). Use this to answer questions like 'which models got cheaper this month?' or 'which providers raised prices recently?'
| Parameter | Type | Required | Notes |
|---|---|---|---|
| days | integer | no | Look-back window in days (default: 30, max: 365) |
| limit | integer | no | Maximum models to return (default: 20, max: 100) |
Register a webhook URL to receive notifications when a model's price changes by more than a specified percentage. Optionally scope the alert to a specific provider or model. Returns the alert ID.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Webhook URL to POST when the alert fires |
| threshold_pct | number | no | Minimum absolute % price change to trigger the alert (default: 5.0) |
| provider | string | no | Limit to a specific provider (e.g. 'openai'). Omit for all. |
| model_name | string | no | Limit to a specific model name. Omit for all models. |
List all registered price-change webhook alerts with their IDs and settings.
No parameter schema on file.
Delete a registered price-change alert by its ID.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| alert_id | integer | yes | The ID of the alert to delete (from list_price_alerts or register_price_alert) |
Generate a download URL for the pricing history export. Returns a URL the user can open in their browser to download snapshot history as CSV (for spreadsheets) or JSON (for code). Use this when the user asks to export, download, or save pricing data.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| format | string | no | Output format: 'csv' (default) or 'json' |
| model_name | string | no | Filter by model name (optional) |
| provider | string | no | Filter by provider (optional) |
| days | integer | no | Look-back window in days (default: 30, max: 365) |
| limit | integer | no | Max rows to export (default: 10000, max: 100000) |
List stored chat conversation sessions with their IDs, last-updated timestamp, turn count, and a preview of the most recent user message. Use this when the user asks to see their past conversations or chat history.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | Maximum number of conversations to return (default: 20, max: 100) |
Delete a specific chat conversation by its ID. Use when the user asks to delete, clear, or remove a past conversation. Use list_conversations first to find the conversation ID.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| conversation_id | string | yes | The ID of the conversation to delete |
Get subscription pricing for AI coding IDE tools: GitHub Copilot, Cursor, Windsurf, Claude.ai, JetBrains AI, Amazon Q Developer, and Tabnine. Returns monthly subscription cost, inline completion support, context window, and per-tool strengths. Use this when the user asks to compare IDE AI tools, subscription-based coding assistants, or wants to know which IDE AI fits their budget.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | no | Filter by provider name (partial match, case-insensitive). Examples: 'GitHub Copilot', 'Cursor', 'Windsurf', 'JetBrains', 'Amazon Q', 'Tabnine' |
| max_monthly | number | no | Only return plans at or below this monthly USD price (e.g. 20 for $20/mo) |
| inline_only | boolean | no | If true, only return tools that support real-time inline code completion |
Predict the real cost of an LLM call from your actual prompt text — no need to know token counts in advance. Counts tokens locally, infers the task type (or accepts one explicitly), estimates output length from empirical I/O profiles, and returns all models ranked cheapest-first with effective cost after prompt-cache savings. Also surfaces the best quality-per-dollar pick. Use this before making a
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prompt | string | yes | The actual prompt text to cost-estimate (required) |
| task_type | string | no | Task type for output-length estimation. Auto-inferred from prompt if omitted. Options: classification, extraction, summarization, qa, code_generation, translation, chat, content_generation, reasoning, |
| top_n | integer | no | Number of models to return, ranked cheapest-first (default: 10, max: 50) |
| cache_hit_ratio | number | no | Fraction of calls that hit the prompt cache (0–1). Set this if you have a large reusable system prompt. Supported providers: Anthropic (10% cache rate), OpenAI (50%), Google (25%). Default: 0 |
| require_function_calling | boolean | no | Only include models that support function/tool calling (default: false) |
| require_vision | boolean | no | Only include models that support image/vision input (default: false) |
| min_context_tokens | integer | no | Minimum context window size required in tokens (optional) |
Optimise a multi-task LLM workload by assigning the cheapest qualifying model to each task instead of running everything through one model. Takes a list of workloads (task type + monthly volume + optional quality floor and capability requirements) and returns a per-task model allocation, the total monthly cost, and the saving versus the best single-model deployment. If a monthly budget is given, l
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workloads | array | yes | One entry per task type in the workload mix |
| monthly_budget_usd | number | no | Total monthly budget in USD. Leftover headroom is spent on the most cost-efficient quality upgrades. |
| min_quality_score | number | no | Global quality floor (0-100) applied to every workload |
Recommend the optimal LLM model from a free-text description of your use case — no need to already know the routing engine's task_type vocabulary. Classifies the description into a task type, then runs it through the same routing engine behind /router/recommend (live pricing + benchmark quality, hard filters for cost/quality/context window, scored by quality-per-dollar). Returns the best match plu
| Parameter | Type | Required | Notes |
|---|---|---|---|
| description | string | yes | Free-text description of the use case, e.g. 'summarize long customer support tickets' or 'generate Python unit tests' |
| task_type | string | no | Optional explicit task type, bypassing auto-classification of the description. Options: classification, extraction, summarization, qa, code_generation, translation, chat, content_generation, reasoning |
| max_cost_per_1m_tokens | number | no | Maximum acceptable average cost per 1M tokens (USD) |
| min_quality_score | number | no | Minimum required quality score (0-100) |
| min_context_window | integer | no | Minimum required context window size (tokens) |
| preferred_provider | string | no | Preferred provider name (10% score boost applied) |
| prefer_low_latency | boolean | no | Prioritise lower-latency models (default: false) |
| exclude_reasoning_models | boolean | no | Exclude slow thinking/reasoning models (default: false) |
| ide_context | string | no | IDE context hint — boosts IDE-native tools: 'copilot' | 'cursor' | 'windsurf' | 'claude_code' | 'jetbrains' | 'amazon_q' |
| monthly_budget_usd | number | no | Monthly spend ceiling in USD. Combined with estimated_monthly_requests, avg_input_tokens, and avg_output_tokens to hard-filter models that would exceed it. |
| estimated_monthly_requests | integer | no | Estimated requests per month (default: 1000) |
| avg_input_tokens | integer | no | Average input tokens per request (default: 500) |
| avg_output_tokens | integer | no | Average output tokens per request (default: 200) |
Audit this server's own pricing data against an external reference registry. Prices here are hand-maintained and go stale silently; a price that disagrees with the registry by more than the threshold is automatically withheld from serving the moment it's detected, not just when this tool runs. This reports what's currently withheld and why. The price value itself is never overwritten by the regist
| Parameter | Type | Required | Notes |
|---|---|---|---|
| threshold_pct | number | no | Minimum % difference to report (default: 5) |
| provider | string | no | Limit the audit to one provider (partial, case-insensitive) |
| limit | integer | no | Maximum findings to return (default: 50, max: 200) |
Report an aggregate accuracy summary for the pricing catalogue: what percentage of models have a confirmed, fresh price, how many are currently withheld due to price drift, how many are newly discovered and not yet priced, and how many confirmed prices are over 90 days old. A single trust signal, distinct from check_price_drift which lists individual disputes. Use when the user asks how accurate o
No parameter schema on file.
Report process-lifetime hit/miss counts, total lookups, and hit rate for the ~5-minute recommendation cache, separately for the recommend_model tool and POST /router/recommend (never combined). Server-operations introspection for confirming the cache is reducing recomputation in production, not a pricing question. Counts reset on process restart; reading them never changes them.
No parameter schema on file.
Record actual token usage for a completed LLM call. Cost is computed server-side from current pricing, never trusted from the caller — this is the 'actual spend' counterpart to estimate_cost's hypothetical numbers. Optionally scope to an org_id for per-org spend tracking. Resubmitting the same request_id for the same org is a no-op. Use when the user wants to log or track real LLM spend, not just
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model_name | string | yes | Name of the LLM model that was called |
| input_tokens | integer | yes | Number of input tokens actually used |
| output_tokens | integer | yes | Number of output tokens actually used |
| org_id | string | no | Optional organisation ID to attribute this usage to |
| occurred_at | number | no | Unix timestamp when the call happened (default: now) |
| request_id | string | no | Optional idempotency key — resubmitting the same value is a no-op |
| session_id | string | no | Optional session ID to tag this event with, so it can later be grouped and retrieved via analyze_session_usage — e.g. a bounded burst of calls like a coding-agent run or a chat session |
Get a summary of actual recorded LLM spend: total cost, request count, and breakdowns by model and provider, from usage events previously logged via record_usage. Use when the user asks what they've actually spent, as opposed to a hypothetical cost estimate.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| org_id | string | no | Optional organisation ID filter |
| days | integer | no | Look-back window in days (default: 30, max: 365) |
Analyze one specific session's actual recorded LLM usage (tagged via record_usage's session_id) on demand: total input/output tokens, total actual cost, and a per-model breakdown if more than one model was used. Also runs the session's own observed token pattern through the same routing engine behind recommend_model / POST /router/recommend to produce a grounded recommendation — or confirm the cur
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | The session_id previously used when calling record_usage |
| org_id | string | no | Optional organisation ID filter — scopes the lookup to usage events recorded under that org_id, same as get_usage_summary's org_id |
Bulk-import a completed session's usage in a single call — the retroactive counterpart to record_usage, for when a session wasn't instrumented live. Use when a calling agent (e.g. VS Code Copilot Chat) already has a session's turn-by-turn history in its own local store and wants this server to report on it exactly as if it had been tracked live. Accepts a list of entries under one shared session_i
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | Shared session ID to tag every entry in this batch with |
| org_id | string | no | Optional organisation ID to attribute this usage to |
| entries | array | yes | Usage entries to import, one per turn/call in the session |
Register a webhook URL to receive notifications when actual recorded spend (from record_usage) crosses a USD threshold within a rolling window. Optionally scope to a specific org_id (omit for total spend across all orgs). Fires at most once per period_days while spend stays over threshold. Returns the alert ID.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Webhook URL to POST when the alert fires |
| threshold_usd | number | yes | Spend level in USD that triggers the alert |
| org_id | string | no | Organisation to monitor. Omit for total spend across all orgs. |
| period_days | integer | no | Rolling look-back window for the spend check, in days (default: 30) |
List all registered budget-spend webhook alerts with their IDs and settings.
No parameter schema on file.
Delete a registered budget-spend alert by its ID.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| alert_id | integer | yes | The ID of the alert to delete (from list_budget_alerts or register_budget_alert) |
Ask the LLM Pricing AI agent a question in natural language. Use for complex queries about pricing, model recommendations, cost optimisation advice, or anything that benefits from multi-step reasoning.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| message | string | yes | The question or task for the pricing agent |
| conversation_id | string | no | Optional conversation ID to continue a previous session |
| autonomous | boolean | no | Run in autonomous task mode (default: false) |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install LLM Pricing or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 100 / 100
Release 1.1.0 · scanned 30 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score100
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationsource
Surface digest35d969a418d004155251d6fc63ff32051bda2bb0c811dd194df70c6ba0cf302d
Score vectorthreat 100 → client 100
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
No tool surface was enumerated, so there is nothing to attribute a capability to.
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest35d969a418d00415
Scanned2026-10-30
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.1.0. Pin a release below and the command asks for exactly that one.
1.1.0
29 Oct 2026
latestNo release note was published with this version.
1.0.2
25 Oct 2026
No release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish LLM Pricing can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.