AI & Machine Learning

llmap.ai

An MCP server for AI model hardware compatibility, recommending GPUs/Apple Silicon, comparing buy vs rent, and providing model specs and benchmarks.

1 endpoint14 known toolsFirst detected September 12, 2026Last detected September 12, 2026

ENDPOINT 1

https://llmap.ai/mcp

No auth detected

MCP server metadata

Name: llmap
Version: 0.1.0

Capabilities

toolsresourcesprompts

Known tools 14

check_fit

Check whether a model runs on given hardware: verdict (runs/offloads/wont_fit/hosted), usable context, estimated decode speed.

Inferred read-only

get_hardware

Full spec sheet for a GPU or Apple Silicon chip by slug.

Inferred read-only

recommend_hardware

Recommend hardware for a model, budget, and workload, with fit and speed for each pick.

Inferred read-only

compare_buy_vs_rent

Break-even analysis: buying hardware vs renting hosted inference for a monthly token volume.

Inferred read-only

get_model

Full model card: specs, quants, license terms, benchmark scores, and where to run it.

Inferred read-only

search_models

Search/filter the model catalog by name, size, vendor, modality, license, or what fits in a given memory budget.

Inferred read-only

list_provider_offers

Hosted offers for a model, each carrying its own billingUnit (per_1m_tokens, per_audio_minute or per_1m_characters) — never compare prices across units.

Inferred read-only

get_provider

Provider profile: models served, pricing, endpoint regions, privacy policies.

Inferred read-only

get_benchmarks

Benchmark scores for one model, optionally filtered by category.

Inferred read-only

get_leaderboard

Ranked models by benchmark performance with price and fit context; sortable by score, score-per-dollar, or score-per-GB-VRAM; filterable by price, VRAM, license, or EU hosting.

Inferred read-only

compare_models

Side-by-side comparison of 2-5 models: specs, benchmarks, pricing, and fit on the given hardware.

Inferred read-only

get_license_terms

Structured license terms for a model: commercial use, redistribution, MAU caps, restrictions.

Inferred read-only

whats_new

Recent LLM ecosystem events: model releases, price changes, deprecations, license changes.

Inferred read-only

search_guides

Search LLMap guides and articles.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.llmap]
url = "https://llmap.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "llmap": {
      "type": "http",
      "url": "https://llmap.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: llmap
Remote MCP URL: https://llmap.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "llmap": {
      "url": "https://llmap.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "llmap": {
      "type": "http",
      "url": "https://llmap.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "llmap",
  "transport": "streamable-http",
  "url": "https://llmap.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.