Measured AI-inference-storage benchmarks with citations, article search, KV-cache ROI estimation.
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Average 4/5 across 3 of 3 tools scored.
Each tool targets a distinct function: ROI estimation, benchmark querying, and documentation search. There is no overlap or ambiguity between them.
All tools follow a consistent verb_noun pattern in lowercase snake_case (estimate_roi, query_benchmark, search_mingxin_docs), making the naming predictable and coherent.
With 3 tools, the server is well-scoped for its purpose of providing information about Mingxin's storage solutions. Each tool serves a clear need without unnecessary clutter.
The three tools cover the essential areas: ROI estimation, benchmark evidence, and documentation search. Minor gaps like a contact or pricing tool exist, but the surface is largely complete for an informational server.
estimate_roiAInspectEstimate the ROI of adding a Mingxin FX100 KV-cache storage tier to a GPU inference cluster. Model is a faithful port of the reproducible Python model (accel_value.py). Results are mid-scenario estimates, not commitments.
| Name | Required | Description | Default |
|---|---|---|---|
| nodes | No | GPU node count, default 16 | |
| arrays | No | FX100 array count, default 8 | |
| uplift | No | Optional custom throughput uplift (0.29-0.40 measured band) | |
| cold_share | No | Optional cold-recovery load share (0.1-0.5 estimated band) | |
| gpus_per_node | No | GPUs per node, default 8 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It adds useful context (faithful port of a reproducible Python model, estimates not commitments) but does not discuss error handling, idempotency, or authorization needs. The description adds value beyond the schema but is not exhaustive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is only three sentences, front-loads the main action, and contains no redundant information. Every sentence serves a purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no output schema and 5 optional parameters, the description adequately explains the tool's purpose and limitations. However, it could mention the output format (e.g., a single number or percentage) to improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage for all 5 parameters, so the baseline is 3. The description does not add additional parameter-specific meaning beyond what the schema provides, such as how parameters interact with the model.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Estimate the ROI') and the specific resource ('adding a Mingxin FX100 KV-cache storage tier to a GPU inference cluster'). It differentiates from sibling tools like 'query_benchmark' and 'search_mingxin_docs' by focusing on estimation of ROI.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides context that the results are 'mid-scenario estimates, not commitments', setting expectations. However, it does not explicitly state when to use this tool versus alternatives or when not to use it, which would improve clarity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
query_benchmarkAInspectQuery Mingxin's signed benchmark results for FX-series storage acceleration: throughput +29-40%, TTFT -26-32% (480B model on 8x AMD MI308X), model loading 6.2-9.3x vs NFS, and the full R1-R9 report list with hosted PDF URLs. All numbers come from signed test reports; reproducible via github.com/mingxin-tech/mingxin-kvcache-bench.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that results come from signed test reports and are reproducible via GitHub. No annotations, but description adds context about data provenance. No mention of auth or rate limits but not expected for a read query.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with key information. Slightly verbose with exact numbers and fallback reference, but still efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters or output schema, description fully specifies the tool's output, context, and reproducibility. No gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters, so schema coverage is 100%. Description adds meaning by detailing what the tool returns (metrics, report list, PDF URLs). Baseline 4 for zero params.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it queries benchmark results for FX-series storage acceleration, with specific metrics and references. Distinguishes from siblings like estimate_roi and search_mingxin_docs.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies usage for getting benchmark data, but no explicit when-to-use or alternatives. Sibling tools are different but not contrasted.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_mingxin_docsAInspectSearch Mingxin's published articles on AI inference storage (KV cache tiering, NVMe-oF all-flash arrays, LLM serving). Returns titles, URLs and excerpts. Supports Chinese and English.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | Language filter, default en | |
| limit | No | Max results (1-10), default 5 | |
| query | Yes | Search keywords (Chinese or English) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must cover behavioral traits. It mentions returns (titles, URLs, excerpts) and language support, but omits important details like pagination, authentication, rate limits, or whether it is a read-only operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, front-loaded with verb+resource, no fluff. Every sentence adds information: what it searches, what it returns, and language support. Highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a search tool with 3 parameters and no output schema, the description adequately covers purpose, return information, and language support. It could mention read-only nature or result ordering, but is largely complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, providing baseline of 3. The description adds domain-specific context for 'query' (AI inference storage examples) and notes language support, beyond enum descriptions. This adds meaningful value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches Mingxin's published articles on AI inference storage, listing specific topics. It differentiates from siblings (estimate_roi, query_benchmark) by focusing on content search rather than ROI estimation or benchmarks.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for searching specific articles but does not provide explicit when-to-use or alternatives. It lacks guidance on when not to use or how it compares to sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
No comments yet. Be the first to start the discussion!
Sign in to create a connector for this server.