mcp-registry/io.github.skakumanu/llm-pricing-mcp-server · registry v1.79.1 · server reports v1.90.3
Also listed as github/skakumanu/llm-pricing-mcp-server
claude mcp add --transport http glimind https://glimind.com/mcp?ref=install-server. Other clientsAs of 2026-11-22 16:26 UTC, the LLM Pricing MCP server is up with a Glimind reliability score of 82/100 (grade B). Over the last 30 days it answered 99.6% of Glimind's liveness checks. It had 3 outages in 90 days, with a median recovery of 6 minutes.
Real-time, drift-verified LLM pricing across 31 providers with cost+quality model routing.
Point your MCP client at this streamable-http endpoint: https://llm-pricing-api.fly.dev/mcp
1 tool definition(s) exceed ~1,200 tokens each (largest: dispatch, ~1,306).
Move long reference material out of descriptions (link a doc or expose a resource), drop repeated examples, and collapse large enums. Trimming these to ~600 tokens saves ~706 tokens every session. How to fix →
32 of 32 tool(s) carry no readOnlyHint/destructiveHint annotations.
Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →
3 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.
Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →
Negotiates MCP 2024-11-05. Structured output, tool output schemas and elicitation arrived in 2025-06-18.
Upgrade the MCP SDK and negotiate 2025-06-18 or newer. How to fix →
No tool declares an outputSchema.
Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. All of them as JSON: /v1/readiness/mcp-registry%2Fio.github.skakumanu%2Fllm-pricing-mcp-server/fixes
{
"name": "analyze_session_usage",
"description": "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",
"inputSchema": {
"type": "object",
"required": [
"session_id"
],
"properties": {
"org_id": {
"type": "string",
"description": "Optional organisation ID filter — scopes the lookup to usage events recorded under that org_id. Defaults to, and must match, the org of the service key on the MCP connection"
},
"session_id": {
"type": "string",
"description": "The session_id previously used when calling record_usage"
}
}
},
"annotations": {
"readOnlyHint": true
}
}{
"name": "check_price_drift",
"description": "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 s",
"inputSchema": {
"type": "object",
"required": [],
"properties": {
"limit": {
"type": "integer",
"default": 50,
"maximum": 200,
"minimum": 1,
"description": "Maximum findings to return (default: 50, max: 200)"
},
"provider": {
"type": "string",
"description": "Limit the audit to one provider (partial, case-insensitive)"
},
"threshold_pct": {
"type": "number",
"default": 5,
"minimum": 0,
"description": "Minimum % difference to report (default: 5)"
}
}
},
"annotations": {
"readOnlyHint": true
}
}{
"name": "compare_costs",
"description": "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.",
"inputSchema": {
"type": "object",
"required": [
"model_names",
"input_tokens",
"output_tokens"
],
"properties": {
"client": {
"type": "string",
"description": "Your MCP client / coding tool, so only models it can run are considered. Recognised: claude_code, claude_desktop, cursor, github_copilot, windsurf, cline, continue, zed, jetbrains_ai, gemini_cli, codex_cli, aider, amazon_q, chatgpt_desktop. Case- and separator-insensitive ('Claude Code' = claude_code). Order: explicit client > legacy ide_context > client inferred from the MCP handshake (hosted server, best effort) > none. Unknown names return an unfiltered result plus a note."
},
"country": {
"type": "string",
"maxLength": 2,
"minLength": 2,
"description": "Optional ISO-3166 alpha-2 country whose currency to use (e.g. DE -> EUR, IN -> INR). A country whose currency is unsupported yields USD with fallback_to_usd=true."
},
"currency": {
"enum": [
"USD",
"EUR",
"GBP",
"INR",
"JPY",
"CAD",
"AUD",
"BRL",
"CNY",
"SGD",
"CHF",
"KRW",
"MXN"
],
"type": "string",
"description": "Optional ISO-4217 code to convert prices into, alongside the canonical USD figures. Beats country. Unsupported codes return success=false listing the supported set."
},
"model_names": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 50,
"description": "List of model names to compare (at most 50)"
},
"input_tokens": {
"type": "integer",
"minimum": 0,
"description": "Number of input tokens"
},
"output_tokens": {
"type": "integer",
"minimum": 0,
"description": "Number of output tokens"
}
}
},
"annotations": {
"readOnlyHint": true
}
}Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:
curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/io.github.skakumanu/llm-pricing-mcp-server"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/io.github.skakumanu/llm-pricing-mcp-server"}) over MCP.
dispatch ~1,306 tokensrecommend_model ~1,042 tokensoptimize_workload ~795 tokensimport_session_usage ~569 tokenspredict_cost ~544 tokensStatic checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).
Operator? Fix these, then re-check live.
Shows whether the server is live and its agent-readiness score; it updates within the hour.
[](https://glimind.com/server/mcp-registry%2Fio.github.skakumanu%2Fllm-pricing-mcp-server?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fio.github.skakumanu%2Fllm-pricing-mcp-server?ref=badge"><img src="https://glimind.com/badge/mcp-registry%2Fio.github.skakumanu%2Fllm-pricing-mcp-server.svg" alt="MCP server status"></a>
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:b699215e0b0fec4c…, first seen 2026-11-17, included at leaf 312895 of 384,593. Version history · verify what your client received.
Compare: most reliable analytics servers · most reliable knowledge servers · most reliable data servers · most reliable ml servers · most reliable devops servers
Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.
Claude Code
claude mcp add --transport http glimind https://glimind.com/mcp?ref=install-server
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp?ref=install-server"
}
}
}
A free Glimind key lets your agent check whether a server works right now before it calls it, and switch to a live one when it doesn't. No signup, no card.
As of 2026-11-22 16:26 UTC, the LLM Pricing MCP server is up with a Glimind reliability score of 82/100 (grade B). Over the last 30 days it answered 99.6% of Glimind's liveness checks. It had 3 outages in 90 days, with a median recovery of 6 minutes.
LLM Pricing MCP server advertises 32 tools, including analyze_session_usage, ask_agent, check_price_drift, compare_costs, delete_budget_alert.
Point your MCP client at this streamable-http endpoint: https://llm-pricing-api.fly.dev/mcp
Glimind scanned all 32 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.
Status page: 90-day uptime, every outage and how long it lasted.
Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.
Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.