TokenMark MCP
Allows queuing a GitHub repository with benchmark numbers for human review in TokenMark.
Allows queuing a Hugging Face repository with benchmark numbers for human review in TokenMark.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
@altronis/tokenmark-mcp
An MCP server that gives Claude (and other agents) real local-LLM benchmark data + hardware-aware model recommendations from TokenMark.
Ask "what should I run on a Strix Halo for coding?" and the agent answers from measured configs (decode tok/s, quant, backend), each with a source link. It never invents numbers.
Add to Claude Code
claude mcp add tokenmark -- npx -y @altronis/tokenmark-mcpRelated MCP server: inferbench
Add to Cline
Cline CLI:
cline mcp add tokenmark --yes -- npx -y @altronis/tokenmark-mcpCline in VS Code: add the tokenmark entry from the JSON below to cline_mcp_settings.json. Step-by-step notes for agents are in llms-install.md.
Add to any MCP client
Run the server over stdio:
npx -y @altronis/tokenmark-mcpOr in a client config:
{
"mcpServers": {
"tokenmark": {
"command": "npx",
"args": ["-y", "@altronis/tokenmark-mcp"]
}
}
}Tools
tokenmark_recommend:{ hardware, tasks?, prefer?, limit?, cards? }→ ranked model + best-config picks (5 by default, 10 max) with measured tok/s + why.lanesays which lane they came from: GPU cards (RTX 5090, RTX PRO 6000) rank on their own, never against the AI boxes. Naming a card, orcards: true, reads the card lane.tokenmark_configs:{ model?, hardware?, limit?, cards? }→ tracked benchmark configs from one lane, fastest first (25 by default, 50 max;matchedgives the full count), with the run mode (speculative: truefor MTP/DFlash/draft-model runs).other_lanecounts the matches in the other lane.tokenmark_hardware:{ platform? }→ the hardware catalogue (Strix Halo, Gorgon Halo, DGX Spark, Mac Max/Ultra), plusgpu_cardswith measured runs. With a platform: chip specs with a source per value, the boxes that ship it, Singapore prices. With a card ("RTX 5090"): VRAM and bandwidth with sources, and its tracked configs.tokenmark_search:{ term }→ matching models/configs, with GPU-card matches apart undergpu_cards.tokenmark_submit:{ repo, source?, note? }→ queues a GitHub/Hugging Face repo with benchmark numbers for human review.tokenmark_submission_status:{ id }→ where a submission is.tokenmark_submit_result:{ bench_output?, pick?, model?, quant?, hardware?, backend?, decode_tps?, prefill_tps?, ctx?, concurrency?, ..., dry_run? }→ sends a speed the user measured, for human review. Pass raw llama-bench orvllm bench serveoutput asbench_output, or the fields by hand; fields you pass win over what it read. Sending takes two calls:dry_run: truereturns a one-line summary and aconfirmcode; show the user the summary, and once they agree, call again with the same fields andconfirmset to that code. A send without the code, or with fields changed since the dry run, is refused.
Sending measured speeds
tokenmark_submit_result needs a one-time sign-in on the same machine, in a terminal:
npx @altronis/tokenmark-cli loginApprove the short code at https://tokenmark.app/cli. The sign-in can only send results for review and lasts 90 days; the server reads it on every call, so no restart is needed. Where there is no home directory, set TOKENMARK_TOKEN in the server's environment instead. A sign-in is only sent over https (or plain http to this machine), and every sign-in on the account can be revoked at https://tokenmark.app/cli.
Hardware missing from the catalogue, or a result typed in by hand, can also go through the signed-in form at https://tokenmark.app/submit.
Data is pulled live from https://tokenmark.app (override with TOKENMARK_URL). Zero runtime dependencies.
The same data in your terminal
The CLI lives in cli/ of this repo:
npx @altronis/tokenmark-cli recommend --hardware "Strix Halo" --tasks codingThe files in bin/ are the published builds, made from the TokenMark tracker that runs https://tokenmark.app.
MIT licensed. Data aggregated from public community benchmarks with attribution.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Measured local-LLM tok/s on home AI rigs. Search builds, can-it-run, best GPU; sourced + linked.
Read-only: which local LLMs a GPU or Mac can run - VRAM fit, tokens/sec, model specs.
Compare LLM API prices, search models and providers, and access reviewed benchmark results.
GPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceExposes queryable GPU inference benchmark data (quantization, throughput, VRAM, concurrent users) as tools for LLM clients.MIT
- AlicenseNot gradedqualityCmaintenanceInferBench's MCP server lets coding agents run, serve and benchmark local LLMs (text + image, llama.cpp + Stable Diffusion) on your own hardware on demand — measuring real tokens/sec and picking the optimal quant for your GPU from a 124-model catalog. Local-first, no cloud required.2MIT
- AlicenseNot gradedqualityDmaintenanceEnables benchmarking of local LLM models (performance and quality) and sharing results to a public leaderboard via MCP tools.16 npm8Apache 2.0
- AlicenseNot gradedqualityBmaintenanceVendor-neutral local LLM inference benchmark and hardware-config advisor for mlx and llama.cpp. Exposes an MCP tool that measures real tokens/second on your own hardware.11 npmApache 2.0