This server is a read-only MCP interface to AGmind's registry of measured local-LLM benchmark claims, letting you search, retrieve, and enumerate benchmark evidence with citations.
Search claims: keyword search across headline, metric, system, model, runtime, scope, and id; case-insensitive, all whitespace-separated terms must match; returns summaries with value, unit, evidence level, permalink, and citation.
Get full claim: fetch a single claim by id with the complete statement, measured value, workload scope, limitations, evidence level, raw run ids/links, derivation SQL, permalink, and citation string.
List measured configurations: view distinct system × model × runtime combinations that have published claims, including claim counts and example ids.
Safe, read-only operation: no writes, telemetry, or accounts; the server only fetches and caches the registry from agmind.ai (or a mirror via AGMIND_CLAIMS_URL) and performs substring matching.
MCP integration: can be added to MCP clients like Claude Code or Claude Desktop via npx from the pinned GitHub release, and communicates over stdio.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@agmind-mcp search claims for TTFT on Strix Halo with 32k context"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for measured local-LLM benchmarks. It exposes the AGmind Systems Lab claim registry, currently 40 published claims measured on AMD Strix Halo hardware (Ryzen AI Max+ 395, Radeon 8060S, 128 GB unified memory) running llama.cpp on Vulkan and ROCm backends, as three read-only Model Context Protocol tools. Two NVIDIA DGX Spark (GB10) nodes are on the same lab bench; their claims enter the registry as runs are published. The lab has separately published vLLM work on DGX Spark; registry claims for it follow the same pipeline.
Every claim is a specific measured number: time to first token, inter-token latency, task success rate, answerless-response rate, long-context needle success, endurance drift. Each carries the exact hardware, runtime build, model revision and quantization, a frozen workload scope, stated limitations, an evidence level, links to the raw run records, and a ready-made citation string. Values are re-derived from raw runs on every CI build of the registry, so the numbers a model quotes through this server match the published evidence.
Requires Node.js 18 or newer. No install step is needed; npx fetches the server from GitHub. Pin the release tag (#v1.0.1) so what runs on your machine is a fixed, reviewable commit rather than whatever main holds at the moment you start it. The package is not published on npm: only the github: form below is ours, and a package named agmind-mcp on the npm registry would not be.
Claude Code
claude mcp add agmind -- npx -y github:botAGI/agmind-mcp#v1.0.1Claude Desktop (claude_desktop_config.json) and other MCP clients that take the standard config shape:
{
"mcpServers": {
"agmind": {
"command": "npx",
"args": ["-y", "github:botAGI/agmind-mcp#v1.0.1"]
}
}
}Releases and their commits: https://github.com/botAGI/agmind-mcp/releases.
From a local clone:
npm install
node server.mjs # speaks MCP over stdio
npm test # spawns the server and drives a real MCP sessionRelated MCP server: Local AI MCP
All three tools are read-only. Results are JSON in a text content block, and every claim in every result carries its cite string and permalink so agents can attribute what they quote.
search_claimsKeyword search over headline, metric, system, model, runtime, scope, and id. Case-insensitive; every whitespace-separated term must match.
search_claims({ "query": "ttft 32k" })Returns {id, headline, value, unit, evidence_level, permalink, cite} per match. Useful queries: decode, answerless, ttft cache, rocm, task-success, endurance.
get_claimOne claim in full by id: the complete answer paragraph, measured value and unit, workload scope, aggregation, limitations, evidence level, raw run ids with GitHub links, the derivation SQL, permalink, and citation string.
get_claim({ "id": "strix.qwen36.docsession.c1.ttft-q2-32k-cache" })An unknown id returns an error listing the closest matching ids.
list_measuredThe distinct system × model × runtime combinations that have published claims, with claim counts and example ids. Call this first to see what has actually been measured.
list_measured({})Server code: Apache-2.0.
Claim data: CC BY 4.0, attribution AGmind Systems Lab (agmind.ai). Each tool result includes a per-claim cite string ready to paste; reuse of the numbers should keep the claim permalink.
Registry source: https://agmind.ai/claims.json. Raw run records and derivation SQL: botAGI/agmind-lab. Benchmark harness and corpora: botAGI/agmind-bench.
Methodology, evidence levels, and errata: agmind.ai/methodology, agmind.ai/errata.
Read-only. The server never writes anything anywhere.
No telemetry, no analytics, no accounts. The only network call is fetching the registry from agmind.ai.
The registry is fetched at startup and cached in memory for one hour; a failed refetch falls back to the cached copy. The fetch times out after fifteen seconds and the response is shape-checked (a claims array of records with string ids) before anything is served to a model. Set AGMIND_CLAIMS_URL to point at a mirror of the registry if needed.
Tool inputs are used only for case-insensitive substring matching over the cached registry; the server builds no regular expressions from them and runs nothing.
Fetch a single claim from the AGmind registry by id: full statement, measured value, unit, scope, limitations, evidence level, raw run ids and links, permalink, and the ready-made citation string. Ids look like "strix.qwen36.interactive2.c1.ttfa-nothink".
Inputs: id (required).
List the distinct system × model × runtime combinations that have published, measured claims in the AGmind registry, with claim counts and example claim ids (with permalinks). Start here to see what hardware and models the lab has qualified.
Inputs: no named parameters.
Keyword search over the AGmind claim registry of measured local-LLM benchmarks (hardware, runtime, model, metric, workload scope). Case-insensitive; every whitespace-separated term must match. Returns claim summaries with value, unit, evidence level, permalink, and a ready-made citation string. Use get_claim for the full record including limitations and raw run ids.
Inputs: query (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 3 tools
Each tool serves a clearly distinct purpose: get_claim retrieves a single record by ID, list_measured provides an overview of measured combinations, and search_claims performs keyword queries. There is no overlap in functionality or potential for misselection.
All tool names follow a consistent snake_case verb_noun pattern (get_claim, list_measured, search_claims), which is predictable and easy to remember. No mixed conventions or ambiguous verbs.
With 3 tools, the set is compact yet sufficient for the server's purpose of querying a claim registry. Each tool earns its place, covering retrieval, overview, and search without unnecessary bloat.
For a read-only registry, the surface is complete: users can search, list overall combinations, and fetch full details by ID. There are no missing lifecycle operations (create/update/delete) that would apply to this domain, so no dead ends remain.
Read-only MCP server for The Quiet Protocol's engines, benchmarks, proof, and business data.
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
Capability registry for the agentic economy. Semantic search over verified MCP server listings.
