LLM Pricing MCP server
io.github.skakumanu/llm-pricing-mcp-serverskakumanustreamable-httpv1.79.1Scanned
Real-time, drift-verified LLM pricing across 31 providers with cost+quality model routing.
32 tools: 3 can delete or cancel things, 1 do something that can't be undone, 12 change things and 16 only read.
- Reads private data · 1
- Reads text others write · 3
- Can send data out · 3
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here can delete or cancel things and 1 does something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the LLM Pricing MCP server can do
The LLM Pricing MCP server is published by the GitHub account skakumanu. It has 32 tools. It can delete or cancel things (3 tools: delete_price_alert, delete_conversation and delete_budget_alert), do things that cannot be undone, such as sending, paying or publishing (dispatch) and create or change data (12 tools: estimate_cost, register_price_alert, get_pricing_export_url, predict_cost and 8 more). 16 tools only read.
1 tool reads private data (list_conversations); 3 tools bring in text other people can write (get_pricing_export_url, list_conversations and get_cache_stats); 3 tools can send data out of your system (register_price_alert, register_budget_alert and dispatch). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 1 finding (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 11, 2026, version 1.79.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
32 tools
Deletes or cancels 3Claude Code: deny
delete_budget_alertDelete one of your org's registered budget-spend alerts by its ID.No findings
Why it is in this group
- The name "delete_budget_alert" says "delete": a word for removing or ending something.
Description, as the server wrote it Delete one of your org's registered budget-spend alerts by its ID. Requires your service API key on the MCP connection (x-api-key or Authorization: Bearer); another org's alert ID reads as not found.
delete_conversationDelete a specific chat conversation by its ID.No findings
Why it is in this group
- The name "delete_conversation" says "delete": a word for removing or ending something.
Description, as the server wrote it 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. Operator only: needs the server operator's key (MCP_API_KEY) on the MCP connection (x-api-key or Authorization: Bearer); any other caller, including the chat agent and the local STDIO server, gets error_code operator_key_required.
delete_price_alertDelete a registered price-change alert by its ID.No findings
Why it is in this group
- The name "delete_price_alert" says "delete": a word for removing or ending something.
Description, as the server wrote it Delete a registered price-change alert by its ID. Operator only: needs the server operator's key (MCP_API_KEY) on the MCP connection (x-api-key or Authorization: Bearer); any other caller, including the chat agent and the local STDIO server, gets error_code operator_key_required. To view or delete an alert you registered yourself, use manage_price_alert with the alert_token from registration.
Can't be undone 1Claude Code: ask
dispatchSend a text chat request through the dispatch gateway: it applies your policy, runs the best eligible model, and returns the completion, usage and the full dispatch_receipt (chosen…Can send data outNo findings
Why it is in this group
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe description's first verb is "send": it sends or publishes something to other people.
Description, as the server wrote it Send a text chat request through the dispatch gateway: it applies your policy, runs the best eligible model, and returns the completion, usage and the full dispatch_receipt (chosen model, reason, cost, savings, attempts) — the same as POST /v1/chat/completions with a `dispatch` object. This makes a REAL model call billed to your own provider keys stored for your org (POST /dispatch/keys), and the spend is recorded against your org. Requires your service API key on the MCP connection (x-api-key or Authorization: Bearer); the operator key and anonymous callers get dispatch_requires_api_key, and the local STDIO server refuses with dispatch_requires_hosted_mcp. Pass prompt (with optional system) or messages, not both. Text-only, single-choice, non-streaming; no tools/functions. Refusals carry the same error codes as HTTP. Calls can take a while with failover: bound them with dispatch.failover.timeout_ms and dispatch.failover.max_attempts, and set LLM_PRICING_MCP_TIMEOUT_MS=120000 when using the npx bridge.
Changes things 12Claude Code: ask
ask_agentAsk the LLM Pricing AI agent a question in natural language.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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.
check_price_driftAudit this server's own pricing data against an external reference registry.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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 registry. Use when the user asks whether the pricing data is accurate or up to date, or wants to audit a specific provider's rates.
estimate_costEstimate the cost of using a specific LLM modelNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Estimate the cost of using a specific LLM model
get_pricing_export_urlGenerate a download URL for the pricing history export.Reads text others writeNo findings
Why it is in this group
- The name "get_pricing_export_url" says "get": a word for reading.
- The description's first verb is "generate": a word for a change.
What it can reach
- untrusted-inputThe name "get_pricing_export_url" says "get" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "generate" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it 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.
import_session_usageBulk-import a completed session's usage in a single call — the retroactive counterpart to record_usage, for when a session wasn't instrumented live.No findings
Why it is in this group
- The name "import_session_usage" says "import": a word for a change.
Description, as the server wrote it 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_id; each entry resolves its input and output tokens independently, either from exact counts when known or by estimating from raw turn text using this server's existing token counter. Cost is always computed server-side from current pricing, never trusted from the caller. A malformed entry (no usable tokens/text on one side, or an unresolvable model_name) is reported as its own per-entry failure and does not fail the rest of the batch. Idempotent like record_usage — resubmitting the same entries (same request_id, or the same session_id/model/occurred_at/token-or-text when request_id is omitted) is a no-op. Recorded usage is then readable via analyze_session_usage and GET /usage/session/{session_id}. Requires your service API key on the MCP connection (x-api-key or Authorization: Bearer); org_id defaults to, and must match, that key's org. POST /mcp request bodies are capped at 1,000,000 bytes (413 above that). 500 exact-count entries fit comfortably (~150 KB); text-mode imports of long sessions can exceed it, so split the entries across several calls under the same session_id — imports are idempotent, so overlapping or retried batches are safe.
optimize_workloadOptimise a multi-task LLM workload by assigning the cheapest qualifying model to each task instead of running everything through one model.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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, leftover headroom is spent on the most cost-efficient quality upgrades. Use when the user asks how to cut LLM spend across several task types, or whether tiered model routing is worth it. Pass client (e.g. 'claude_code', 'cursor', 'github_copilot', 'cline') so the answer is restricted to models that tool can run; omit it and the hosted server tries to infer it from the MCP handshake, otherwise every priceable model is considered. An explicit client always wins. Recognised clients: claude_code, claude_desktop, cursor, github_copilot, windsurf, cline, continue, zed, jetbrains_ai, gemini_cli, codex_cli, aider, amazon_q, chatgpt_desktop.
predict_costPredict the real cost of an LLM call from your actual prompt text — no need to know token counts in advance.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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 any LLM API call to avoid surprise bills.
recommend_modelRecommend 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.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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 plus up to 3 alternatives. Read-only — use predict_cost first if you also want per-model cost estimates for an actual prompt, and optimize_workload if you have several distinct task types to route at once. Restricts (not just boosts) the candidate set to models your client can run before ranking. Pass client (e.g. 'claude_code', 'cursor', 'github_copilot', 'cline') so the answer is restricted to models that tool can run; omit it and the hosted server tries to infer it from the MCP handshake, otherwise every priceable model is considered. An explicit client always wins. Recognised clients: claude_code, claude_desktop, cursor, github_copilot, windsurf, cline, continue, zed, jetbrains_ai, gemini_cli, codex_cli, aider, amazon_q, chatgpt_desktop.
record_usageRecord actual token usage for a completed LLM call.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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. Usage is attributed to your org. 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 estimate it. Requires your service API key on the MCP connection (x-api-key or Authorization: Bearer); org_id defaults to, and must match, that key's org.
register_budget_alertRegister a webhook URL to receive notifications when actual recorded spend (from record_usage) crosses a USD threshold within a rolling window.Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Register a webhook URL to receive notifications when actual recorded spend (from record_usage) crosses a USD threshold within a rolling window. The alert monitors your org's spend. Fires at most once per period_days while spend stays over threshold. Returns the alert ID. Requires your service API key on the MCP connection (x-api-key or Authorization: Bearer); org_id defaults to, and must match, that key's org.
register_price_alertRegister a webhook URL to receive notifications when a model's price changes by more than a specified percentage.Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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 and a one-time alert_token needed to view or delete it via manage_price_alert.
support_chatAsk the customer support assistant about THIS service: plans and prices, signing up, upgrading or cancelling, invoices, service API keys (rotation, lost key), rate limits, connecti…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Ask the customer support assistant about THIS service: plans and prices, signing up, upgrading or cancelling, invoices, service API keys (rotation, lost key), rate limits, connecting over MCP or REST, data accuracy, and how to reach the owner. Answers come only from the published FAQ, the plan catalogue and the caller's own account; anything the assistant cannot do (refunds, credits, disputes, lost key without the current key, 'talk to a human', security reports) is escalated to the owner with a reference. Identity-aware: with your service key on the MCP connection (x-api-key or Authorization: Bearer) it can describe your own plan, payment status, rate limit and key preview; without a key it answers in general. It never reveals keys or other customers' data, never changes billing, and is capped per caller per day (a cap hit returns a non-LLM fallback with FAQ links). The local STDIO server refuses with support_requires_hosted_mcp.
Only reads 16Show 16 read-only tools
analyze_session_usageAnalyze 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 i…No findings
Why it is in this group
- The name "analyze_session_usage" says "analyze": a word for reading.
Description, as the server wrote it 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 current choice is already optimal — with the estimated dollar savings or increase versus this session's actual cost. Returns has_data: false with no recommendation if the session_id has no recorded usage. Advisory only — never switches or reroutes anything. Requires your service API key on the MCP connection (x-api-key or Authorization: Bearer); org_id defaults to, and must match, that key's org.
compare_costsCompare costs for multiple LLM models.No findings
Why it is in this group
- The name "compare_costs" says "compare": a word for reading.
Description, as the server wrote it Compare costs for multiple LLM models. Every named model is priced; pass client (e.g. 'claude_code') to also flag each model runnable_in_client (it never filters here). Recognised clients: claude_code, claude_desktop, cursor, github_copilot, windsurf, cline, continue, zed, jetbrains_ai, gemini_cli, codex_cli, aider, amazon_q, chatgpt_desktop.
get_all_pricingGet current pricing for all LLM models from all providersNo findings
Why it is in this group
- The name "get_all_pricing" says "get": a word for reading.
Description, as the server wrote it Get current pricing for all LLM models from all providers
get_cache_statsReport 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 (nev…Reads text others writeNo findings
Why it is in this group
- The name "get_cache_stats" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
Description, as the server wrote it 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.
get_data_qualityReport 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 man…No findings
Why it is in this group
- The name "get_data_quality" says "get": a word for reading.
Description, as the server wrote it 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 or trustworthy the pricing data is, overall.
get_ide_pricingGet subscription pricing for AI coding IDE tools: GitHub Copilot, Cursor, Windsurf, Claude.ai, JetBrains AI, Amazon Q Developer, and Tabnine.No findings
Why it is in this group
- The name "get_ide_pricing" says "get": a word for reading.
Description, as the server wrote it 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.
get_performance_metricsGet performance metrics (throughput, latency, context window) for modelsNo findings
Why it is in this group
- The name "get_performance_metrics" says "get": a word for reading.
Description, as the server wrote it Get performance metrics (throughput, latency, context window) for models
get_pricing_historyQuery historical pricing snapshots recorded over time.No findings
Why it is in this group
- The name "get_pricing_history" says "get": a word for reading.
Description, as the server wrote it 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.
get_pricing_trendsFind models whose prices changed the most over a given period.No findings
Why it is in this group
- The name "get_pricing_trends" says "get": a word for reading.
Description, as the server wrote it 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?'
get_telemetryGet MCP server telemetry and usage statistics including tool usage, response times, and error ratesNo findings
Why it is in this group
- The name "get_telemetry" says "get": a word for reading.
Description, as the server wrote it Get MCP server telemetry and usage statistics including tool usage, response times, and error rates
get_usage_summaryGet 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.No findings
Why it is in this group
- The name "get_usage_summary" says "get": a word for reading.
Description, as the server wrote it 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. Requires your service API key on the MCP connection (x-api-key or Authorization: Bearer); org_id defaults to, and must match, that key's org.
get_use_casesGet recommended use cases and strengths for LLM modelsNo findings
Why it is in this group
- The name "get_use_cases" says "get": a word for reading.
Description, as the server wrote it Get recommended use cases and strengths for LLM models
list_budget_alertsList your org's registered budget-spend webhook alerts with their IDs and settings.No findings
Why it is in this group
- The name "list_budget_alerts" says "list": a word for reading.
Description, as the server wrote it List your org's registered budget-spend webhook alerts with their IDs and settings. Requires your service API key on the MCP connection (x-api-key or Authorization: Bearer); only alerts for that key's org are returned.
list_conversationsList stored chat conversation sessions with their IDs, last-updated timestamp, turn count, and a preview of the most recent user message.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "list_conversations" says "list": a word for reading.
What it can reach
- private-dataThe name "list_conversations" says "list" and "conversation": it reads messages.
- private-dataThe description's first sentence says "list" and "chat": it reads messages.
- untrusted-inputThe name "list_conversations" says "list" and "conversation": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "chat": it reads messages, which other people can write.
Description, as the server wrote it 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. Operator only: needs the server operator's key (MCP_API_KEY) on the MCP connection (x-api-key or Authorization: Bearer); any other caller, including the chat agent and the local STDIO server, gets error_code operator_key_required.
list_price_alertsList all registered price-change webhook alerts with their IDs and settings.No findings
Why it is in this group
- The name "list_price_alerts" says "list": a word for reading.
Description, as the server wrote it List all registered price-change webhook alerts with their IDs and settings. Operator only: needs the server operator's key (MCP_API_KEY) on the MCP connection (x-api-key or Authorization: Bearer); any other caller, including the chat agent and the local STDIO server, gets error_code operator_key_required.
manage_price_alertView or delete the one price-change alert you registered, using the alert_token that register_price_alert returned once.1 finding
Why it is in this group
- The description's first verb is "view": a word for reading.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...API key needed: the alert_token is the credential and is scoped to exactly that alert. ac..."
Description, as the server wrote it View or delete the one price-change alert you registered, using the alert_token that register_price_alert returned once. No API key needed: the alert_token is the credential and is scoped to exactly that alert. action 'view' returns its id, url, threshold_pct, provider, model_name and created_at; action 'delete' stops it. A token that matches nothing gets the same invalid_alert_token refusal whether or not any alert exists. Alerts registered before v1.81.0 have no token and are removed via the operator.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
9 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out3
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__llm-pricing__list_conversations"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:11 UTC, unchanged since Nov 6, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 16
- Protocol version
- 2024-11-05
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 16 tools that change things (3 destructive, 1 irreversible, 12 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://llm-pricing-api.fly.dev/mcp: tools/list returned 32 tools to an anonymous client, including delete_price_alert (destructive), delete_conversation (destructive), delete_budget_alert (destructive), dispatch (irreversible), estimate_cost (write) and 11 more
Posture changes
- Nov 6, 2026
- Tools that change things, listed without credentials: 14 to 16
Findings
Matches of fixed checks, with the text they matched.
The description mentions "credential".
What this check looks forMatched text
description: "...API key needed: the alert_token is the credential and is scoped to exactly that alert. ac..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools3 added, 15 changed.+3 added~15 changedView diff
- Added:dispatchCan't be undone
- Added:manage_price_alertOnly reads
- Added:support_chatChanges things
- Changed:analyze_session_usageOnly readsdescriptioninputSchema
- Changed:compare_costsOnly readsdescriptioninputSchema
- Changed:delete_budget_alertDeletes or cancelsdescription
- Changed:delete_conversationDeletes or cancelsdescription
- Changed:delete_price_alertDeletes or cancelsdescription
- Changed:get_usage_summaryOnly readsdescriptioninputSchema
- Changed:import_session_usageChanges thingsdescriptioninputSchema
- Changed:list_budget_alertsOnly readsdescription
- Changed:list_conversationsOnly readsdescription
- Changed:list_price_alertsOnly readsdescription
- Changed:optimize_workloadChanges thingsdescriptioninputSchema
- Changed:recommend_modelChanges thingsdescriptioninputSchema
- Changed:record_usageChanges thingsdescriptioninputSchema
- Changed:register_budget_alertChanges thingsdescriptioninputSchema
- Changed:register_price_alertChanges thingsdescriptioninputSchema
PostureRemote posture changed. Tools that change things, listed without credentials: 14 -> 16.View diff
- Tools that change things, listed without credentials: 14 to 16
Tools5 changed.~5 changedView diff
- Changed:compare_costsOnly readsinputSchema
- Changed:estimate_costChanges thingsinputSchema
- Changed:get_all_pricingOnly readsinputSchema
- Changed:get_use_casesOnly readsinputSchema
- Changed:recommend_modelChanges thingsinputSchema
Install
Pinned to version 1.79.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http llm-pricing https://llm-pricing-api.fly.dev/mcpclaude mcp add --transport http llm-pricing https://llm-pricing-api.fly.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__llm-pricing__get_all_pricing",
"mcp__llm-pricing__compare_costs",
"mcp__llm-pricing__get_performance_metrics",
"mcp__llm-pricing__get_use_cases",
"mcp__llm-pricing__get_telemetry",
"mcp__llm-pricing__get_pricing_history",
"mcp__llm-pricing__get_pricing_trends",
"mcp__llm-pricing__list_price_alerts",
"mcp__llm-pricing__manage_price_alert",
"mcp__llm-pricing__list_conversations",
"mcp__llm-pricing__get_ide_pricing",
"mcp__llm-pricing__get_data_quality",
"mcp__llm-pricing__get_cache_stats",
"mcp__llm-pricing__get_usage_summary",
"mcp__llm-pricing__analyze_session_usage",
"mcp__llm-pricing__list_budget_alerts"
],
"ask": [
"mcp__llm-pricing__estimate_cost",
"mcp__llm-pricing__register_price_alert",
"mcp__llm-pricing__get_pricing_export_url",
"mcp__llm-pricing__predict_cost",
"mcp__llm-pricing__optimize_workload",
"mcp__llm-pricing__recommend_model",
"mcp__llm-pricing__check_price_drift",
"mcp__llm-pricing__record_usage",
"mcp__llm-pricing__import_session_usage",
"mcp__llm-pricing__register_budget_alert",
"mcp__llm-pricing__dispatch",
"mcp__llm-pricing__ask_agent",
"mcp__llm-pricing__support_chat"
],
"deny": [
"mcp__llm-pricing__delete_price_alert",
"mcp__llm-pricing__delete_conversation",
"mcp__llm-pricing__delete_budget_alert"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as llm-pricing. Review it before you use it.
Capability tags behind 6 rules
- mcp__llm-pricing__register_price_alert outbound
- mcp__llm-pricing__get_pricing_export_url untrusted-input
- mcp__llm-pricing__list_conversations private-data, untrusted-input
- mcp__llm-pricing__get_cache_stats untrusted-input
- mcp__llm-pricing__register_budget_alert outbound
- mcp__llm-pricing__dispatch outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.skakumanu/llm-pricing-mcp-server/verify?hash=3f285c4ddd52b8d803444b536c997634fe8d84bd67ca2b85e49c120206a02997" | jq -e '.changed == false'Pinned hash 3f285c4ddd52, from Nov 11, 2026, 10:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.skakumanu/llm-pricing-mcp-server/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.skakumanu/llm-pricing-mcp-server)Source: MCP Registry · repository. Synced Oct 29, 2026, 21:18 UTC.
LLM Pricing MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the LLM Pricing MCP server safe?
- No scan can promise that. What its definitions show: 32 tools, 16 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the LLM Pricing MCP server delete data?
- Yes. 3 tools can delete, cancel or revoke something: delete_price_alert, delete_conversation and delete_budget_alert.
Can the LLM Pricing MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: dispatch.
What tools does the LLM Pricing MCP server have?
- 32 tools: 3 destructive, 1 irreversible, 12 write, 16 read. delete_price_alert, delete_conversation, delete_budget_alert, dispatch, estimate_cost, register_price_alert, get_pricing_export_url, predict_cost and 24 more.
Does the LLM Pricing MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the LLM Pricing MCP server send data to outside services?
- 3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): register_price_alert, register_budget_alert and dispatch.
Has the LLM Pricing MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 11, 2026. Every change is on this page and in its Atom feed.