Skip to main content
Glama

MakerPortal compute

by ai.makerportal
OverviewDiscussionsAdmin

Server Details

Deterministic engineering solvers: biquad filter design, room eigenmodes, LLM VRAM fit.

If you are the author of this connector, you can claim ownership with GitHub, an HTTP challenge, or a DNS record. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over 21 days
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL

TDQS

A4.1/5.0

Scored across 5 tools

Disambiguation5/5

Each tool targets a completely different computation domain: audio filters, LLM memory sizing, room acoustics, room geometry, and solenoid magnetics. Even the two room-related tools are cleanly separated by output and input (spectral modes vs. recommended proportions).

Naming Consistency4/5

All tool names use camelCase noun-like compounds describing the result: biquad design, LLM VRAM fit, room modes, room shape band, solenoid field. The naming is readable and predictable, though biquadDesign and llmVramFit lean more action-like than the purely noun-based names.

Tool Count5/5

Five tools is a well-scoped size for a compute/calculator server. Each tool is a substantial standalone calculator, and none feels like filler or overlap.

Completeness4/5

Each individual tool is internally thorough, including edge cases, refused inputs, optional fields, and provenance. Because the server presents a broad set of unrelated calculators rather than a single workflow, there is no clear CRUD surface, but the collection feels representative and lacks obvious dead ends.

Available Tools

5 tools
biquadDesignDesign one RBJ-cookbook biquad and report its numerical behaviour.AInspect

Design one RBJ-cookbook biquad and report its numerical behaviour.

The identical function that renders /lab/biquad/{type}/{freq}. Returns coefficients at the requested sample rate, coefficients at every other rate whose Nyquist limit clears the corner, pole/zero geometry, the −3 dB points solved by bisection, a Q sweep, a gain sweep where the type uses gain, and the quantised forms. The 240-point response curve is omitted unless include=curve is passed. Non-finite values (a notch is −∞ at f0; a low-pass is −∞ at Nyquist) are encoded as the strings "Infinity", "-Infinity" and "NaN" — JSON has no other honest option, and null would be a different answer.

Every result carries provenance.canonicalUrl — the published page for these exact inputs, or the lane hub when they are off the published grid.

ParametersJSON Schema
NameRequiredDescriptionDefault
qNoFilter Q. Defaults to the type’s own default. Shelves ignore it (S is fixed at 1, matching Web Audio).
fsNoSample rate in Hz. Defaults to 48000.
freqYesCorner (or centre) frequency f0 in Hz. Must be below Nyquist.
gainNoPeak/shelf gain in dB. Ignored by types that do not use gain.
typeYesFilter type.
includeNoOptional heavy block to include, omitted by default. "curve": The 240-point log-spaced magnitude response, and one per sweep row.

Output Schema

ParametersJSON Schema
NameRequiredDescription
inputsYesThe parsed inputs, echoed back with defaults filled in.
resultYesThe solved analysis. Shape is per-tool.
licenseYes
provenanceYes

TDQS

A4.5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It fully discloses output composition, the omission of the response curve unless requested, quantised forms, non-finite value encoding as strings, and the provenance field. This is exceptionally transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but well structured: a one-sentence summary, a detailed list of returned values, an edge-case note on non-finite JSON encoding, and a provenance note. Every sentence adds operational value with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers return values, optional heavy output, numerical edge cases, encoding decisions, and provenance. Even though an output schema exists, the description goes beyond what structured data alone would convey and leaves no important behavioral gap for an agent invoking this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% parameter description coverage with detailed explanations for q, fs, freq, gain, type, and include. The description adds little beyond the schema because the schema already documents defaults, ranges, and type-specific behavior like shelves ignoring q.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Design one RBJ-cookbook biquad and report its numerical behaviour.' It also names the URL route it mirrors and enumerates exactly what the result contains, so an agent can clearly tell what the tool does even without the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context on what the tool is for and what optional include=curve controls. It does not explicitly name alternatives or exclusion conditions, but the sibling tools are unrelated to biquad design, so no exclusion is necessary.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

llmVramFitDecide whether one LLM fits one accelerator, at every quantization.AInspect

Decide whether one LLM fits one accelerator, at every quantization.

The identical function that renders /lab/llm-vram/{model}/{gpu}. Returns one row per quantization (FP16 through Q3_K_M) with weight bytes and their basis, headroom, the largest context that fits, and the bandwidth-limited decode ceiling; plus the chosen best-fitting quant, the full-precision row, and a five-state verdict. Model geometry comes from each repo’s own config.json and tensor-shape index; accelerator capacity and bandwidth come from the site’s device table.

Every result carries provenance.canonicalUrl — the published page for these exact inputs, or the lane hub when they are off the published grid.

ParametersJSON Schema
NameRequiredDescriptionDefault
gpuYesAccelerator slug.
batchNoConcurrent sequences sharing the cache. Omit it for the published page's 1.
modelYesModel slug.
contextNoContext length in tokens used for the headline verdict. Omit it and the solver takes its own default of 8192, which is what the published page states.
kvBytesNoBytes per KV cache element: 2 for FP16/BF16 cache, 1 for an 8-bit cache. Omit it for the published page's 2.

Output Schema

ParametersJSON Schema
NameRequiredDescription
inputsYesThe parsed inputs, echoed back with defaults filled in.
resultYesThe solved analysis. Shape is per-tool.
licenseYes
provenanceYes

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full burden, and it does real work: it discloses that model geometry is pulled from each repo's config.json and tensor-shape index and that capacity/bandwidth come from the site's device table — signaling this is a computed estimate from static metadata, not a hardware measurement. It also commits to a provenance.canonicalUrl on every result. It stops short of error/edge behavior (unreachable config, unknown model/gpu), so it is not a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded and the three paragraphs each earn their place: output contract, data sources, then provenance. The middle paragraph is a long run-on sentence listing many row fields, which slightly hurts scannability; splitting it would make it a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 5 parameters, 2 enums, and an output schema, the description covers purpose, output shape (per-quant rows, headroom, context ceiling, decode ceiling, verdict), data dependencies, and the provenance contract. The output schema covers the detailed return fields, and the published-page equivalence ('The identical function that renders /lab/llm-vram/{model}/{gpu}') anchors agent expectations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3; the schema already documents batch (concurrent sequences sharing cache), context (token length), kvBytes (cache precision), and both model/gpu enums with defaults and published-page semantics. The description adds little per-parameter meaning beyond restating what the schema already says (e.g., 'Omit it for the published page's 1').

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence states a specific verb+resource+scope — 'Decide whether one LLM fits one accelerator, at every quantization' — and the return contract is enumerated (per-quantization rows, best-fitting quant, five-state verdict). This is unmistakable against the unrelated siblings (biquadDesign, roomModes, roomShapeBand, solenoidField).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when-to-use/when-not-to-use guidance or named alternatives appear; the tool relies on its clear purpose and the fact that its siblings are unrelated domains. The note that it is 'the identical function that renders /lab/llm-vram/{model}/{gpu}' and the provenance behavior 'when they are off the published grid' imply usage context but never spell out selection conditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

roomModesSolve the eigenmodes of a rectangular room.AInspect

Solve the eigenmodes of a rectangular room.

The identical function that renders /lab/room-modes/{w}x{l}x{h}. Dimensions are in feet and are converted at 0.3048 m/ft. Returns every mode below maxFreq, the three axial fundamentals, mode pile-ups (three or more modes within 5 Hz, capped at 200 Hz because dense modes above the Schroeder crossover are desirable rather than a defect), the widest axial gap below 200 Hz, and Schroeder frequencies at RT60 = 0.3 s and 0.6 s. The full mode list is omitted unless include=modes is passed; counts are always present.

Every result carries provenance.canonicalUrl — the published page for these exact inputs, or the lane hub when they are off the published grid.

ParametersJSON Schema
NameRequiredDescriptionDefault
widthYesRoom width in feet.
heightYesCeiling height in feet.
lengthYesRoom length in feet.
includeNoOptional heavy block to include, omitted by default. "modes": Every solved mode and the axial subset, with their (nx, ny, nz) orders.
maxFreqNoHighest mode frequency to solve for, in Hz. Defaults to 300. Mode count scales with volume × frequency³, so a large room and a high maxFreq together are refused with a 400 once the enumeration would exceed 100,000 modes; the error names the maxFreq that would have worked.

Output Schema

ParametersJSON Schema
NameRequiredDescription
inputsYesThe parsed inputs, echoed back with defaults filled in.
resultYesThe solved analysis. Shape is per-tool.
licenseYes
provenanceYes

TDQS

A3.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full transparency burden and mostly succeeds: it reveals unit conversion (0.3048 m/ft), the output summary fields, the include=modes gating, the 200 Hz pile-up cap and rationale, and provenance.canonicalUrl. The only minor gap is that it does not explicitly state the pure-calculation/no-side-effect nature, though that is strongly implied.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loads the core purpose before the detailed return-value semantics. A few clauses are dense, such as the parenthetical explanation of the 200 Hz pile-up cap, but each sentence contributes behavioral or provenance information rather than padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The combination of a 100%-covered input schema, a rich output schema, and this description leaves little missing: units, required dimensions, optional include flag, frequency limits, refusal condition, and provenance are all covered. An agent has everything needed to decide whether to call it and how to set parameters correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, and the description adds real value beyond the schema: it explains that dimensions are converted from feet, that include=modes is an omitted-by-default heavy block, and that maxFreq interacts with room volume to cause refusals that name a working maxFreq. It does not need to restate the schema's field descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Solve the eigenmodes of a rectangular room,' and the body doubles down with the concrete /lab/room-modes/{w}x{l}x{h} mapping. It is unambiguous about what the tool computes, but it never distinguishes itself from the similarly room-acoustics sibling roomShapeBand, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no when-to-use guidance and names no alternative tools or exclusion conditions. An agent can infer it is for room mode calculations, but the tool does not say when roomModes should be preferred over roomShapeBand or why include=modes might be avoided for large rooms.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

roomShapeBandSolve the best rectangular room proportions for a given volume.AInspect

Solve the best rectangular room proportions for a given volume.

The identical function that renders /lab/room-shape/{lo}-{hi}. Give a room volume in cubic feet and get the proportions to build: the length and width as multiples of the ceiling height, the exact dimensions at your volume, the widest axial gap they leave, and how far those proportions sit from a full solve at your exact volume. Also returns the band the volume falls in, that band's guarantee across its whole range, and which Bolt constraints are active at the answer. Five bands cover 800-5,000 cubic feet; a volume outside that range is refused rather than served from the nearest band.

Every result carries provenance.canonicalUrl — the published page for these exact inputs, or the lane hub when they are off the published grid.

ParametersJSON Schema
NameRequiredDescriptionDefault
volumeYesRoom volume in cubic feet. Five bands cover 800–5000 ft³; anything outside that is a 400 naming the range, never an answer from the nearest band.

Output Schema

ParametersJSON Schema
NameRequiredDescription
inputsYesThe parsed inputs, echoed back with defaults filled in.
resultYesThe solved analysis. Shape is per-tool.
licenseYes
provenanceYes

TDQS

A4.1/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full responsibility and delivers richly. It discloses the return contents, the volume band behavior, refusal of out-of-range input, and the presence of provenance.canonicalUrl on every result. It even clarifies that out-of-range volumes are refused rather than served from a neighboring band.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose and then details outputs, constraints, and provenance in a logical order. It is somewhat verbose, and the sentence about the identical rendering function is slightly tangential, but nearly every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a single-parameter tool with an output schema, and the description covers input units, valid range, refusal behavior, output fields, band guarantees, and provenance. Nothing essential for an agent to decide whether to call it and what to expect is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds meaningful semantics beyond the schema: it specifies the valid volume range, the band structure, and the refusal behavior for out-of-range values, which helps the agent reason about valid inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb and resource: solving rectangular room proportions for a given volume. It is unambiguous about what the tool computes, but it does not explicitly distinguish itself from sibling tools such as roomModes, so it misses the top score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The usage context is implied: provide a room volume in cubic feet and receive proportions. It also gives a firm exclusion boundary by refusing volumes outside 800–5,000 cubic feet, but it never names alternatives or states when to prefer another tool, so the guidance is only implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

solenoidFieldSolve the on-axis magnetic field of an air-core solenoid.AInspect

Solve the on-axis magnetic field of an air-core solenoid.

The identical function that renders /lab/solenoid/{diameter}x{length}mm. Returns the centre field per amp-turn and at the requested turns and current, the on-axis profile out to three half-lengths, the span over which the field holds to within 1% and 5% of its centre value, the field at the coil mouth as a fraction of the centre, how far the infinite-solenoid shortcut mu0nI overstates the answer, and the turn count below which the closed form should not be used on this geometry. Dimensions are in millimetres. The field is exactly linear in turns x current, so only that product changes the answer.

Every result carries provenance.canonicalUrl — the published page for these exact inputs, or the lane hub when they are off the published grid.

ParametersJSON Schema
NameRequiredDescriptionDefault
turnsNoNumber of turns. Defaults to 1, which is what the published pages state (their figures are per amp-turn). The field is exactly linear in turns x current.
lengthYesWinding length along the axis, in millimetres.
currentNoWinding current in amperes. Defaults to 1. Only the product of turns and current changes the answer.
diameterYesMean winding diameter in millimetres.

Output Schema

ParametersJSON Schema
NameRequiredDescription
inputsYesThe parsed inputs, echoed back with defaults filled in.
resultYesThe solved analysis. Shape is per-tool.
licenseYes
provenanceYes

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden and does so well: it discloses the returned quantities, the linear dependence on turns x current, millimeter units, and the provenance URL behavior. It does not explicitly state that the operation is side-effect free, but the solver nature makes this sufficiently clear.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact yet information-dense: three paragraphs move from operation to outputs to provenance conventions, with every sentence earning its place. There is no verbose repetition of schema fields or annotations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema exists and the sibling tools are unrelated, the description is complete for correct invocation. It covers units, input semantics, result contents, the linear scaling behavior, and the provenance URL, leaving no critical gap for an agent deciding to call the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already documents all four parameters fully, so the baseline is 3. The description adds valuable cross-parameter semantics by explaining that only the product of turns and current changes the answer and that published figures are per amp-turn, helping the agent choose meaningful inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb-resource pair, 'Solve the on-axis magnetic field of an air-core solenoid,' and then enumerates the concrete outputs. This makes the tool's purpose unambiguous and clearly distinguishes it from the unrelated sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear context by stating that this is the identical function behind a published lab page, which helps an agent know when this tool is the right match. It does not explicitly list exclusions or alternatives, but none of the sibling tools is a plausible candidate for the same calculation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool update
    • ChangedllmVramFit1 field changed
      • changedInput schema / properties / model / enum
        Previous value: -[
-  "deepseek-r1-distill-llama-70b",
-  "deepseek-r1-distill-llama-8b",
-  "deepseek-r1-distill-qwen-1-5b",
-  "deepseek-r1-distill-qwen-14b",
-  "deepseek-r1-distill-qwen-32b",
-  "deepseek-r1-distill-qwen-7b",
-  "dolphin-mistral-24b-venice-edition",
-  "falcon3-7b-instruct",
-  "gemma-2-27b-it",
-  "gemma-2-9b-it",
-  "gemma-3-12b-it",
-  "gemma-3-1b-it",
-  "gemma-3-27b-it",
-  "gemma-3-4b-it",
-  "gpt-oss-120b",
-  "gpt-oss-20b",
-  "granite-3-3-8b-instruct",
-  "hermes-4-3-36b",
-  "hy3",
-  "kat-coder-v2-5-dev",
-  "laguna-s-2-1",
-  "laguna-xs-2-1",
-  "llama-3-1-70b-instruct",
-  "llama-3-1-8b-instruct",
-  "llama-3-1-nemotron-70b-instruct",
-  "llama-3-2-1b-instruct",
-  "llama-3-2-3b-instruct",
-  "llama-3-3-70b-instruct",
-  "minicpm5-1b",
-  "mistral-7b-instruct-v0-3",
-  "mistral-nemo-instruct-2407",
-  "mistral-small-24b-instruct-2501",
-  "mixtral-8x7b-instruct-v0-1",
-  "nanbeige4-2-3b",
-  "olmo-2-1124-13b-instruct",
-  "phi-3-5-mini-instruct",
-  "phi-4",
-  "phi-4-mini-instruct",
-  "qwen-agentworld-35b-a3b",
-  "qwen2-5-0-5b-instruct",
-  "qwen2-5-1-5b-instruct",
-  "qwen2-5-14b-instruct",
-  "qwen2-5-32b-instruct",
-  "qwen2-5-3b-instruct",
-  "qwen2-5-72b-instruct",
-  "qwen2-5-7b-instruct",
-  "qwen2-5-coder-32b-instruct",
-  "qwen2-5-coder-7b-instruct",
-  "qwen3-0-6b",
-  "qwen3-1-7b",
-  "qwen3-14b",
-  "qwen3-30b-a3b",
-  "qwen3-32b",
-  "qwen3-4b",
-  "qwen3-8b",
-  "qwq-32b",
-  "qwythos-9b-claude-mythos-5-1m",
-  "smollm2-1-7b-instruct",
-  "smollm2-135m-instruct",
-  "smollm2-360m-instruct",
-  "tinyllama-1-1b-chat-v1-0",
-  "yi-1-5-34b-chat"
-]New value: +[
+  "deepseek-r1-distill-llama-70b",
+  "deepseek-r1-distill-llama-8b",
+  "deepseek-r1-distill-qwen-1-5b",
+  "deepseek-r1-distill-qwen-14b",
+  "deepseek-r1-distill-qwen-32b",
+  "deepseek-r1-distill-qwen-7b",
+  "dolphin-mistral-24b-venice-edition",
+  "falcon3-7b-instruct",
+  "gemma-2-27b-it",
+  "gemma-2-9b-it",
+  "gemma-3-12b-it",
+  "gemma-3-1b-it",
+  "gemma-3-27b-it",
+  "gemma-3-4b-it",
+  "gpt-oss-120b",
+  "gpt-oss-20b",
+  "granite-3-3-8b-instruct",
+  "hermes-4-3-36b",
+  "hy3",
+  "k2-horizon-7b",
+  "kat-coder-v2-5-dev",
+  "laguna-s-2-1",
+  "laguna-xs-2-1",
+  "llama-3-1-70b-instruct",
+  "llama-3-1-8b-instruct",
+  "llama-3-1-nemotron-70b-instruct",
+  "llama-3-2-1b-instruct",
+  "llama-3-2-3b-instruct",
+  "llama-3-3-70b-instruct",
+  "minicpm5-1b",
+  "minicpm5-2b",
+  "mistral-7b-instruct-v0-3",
+  "mistral-nemo-instruct-2407",
+  "mistral-small-24b-instruct-2501",
+  "mixtral-8x7b-instruct-v0-1",
+  "nanbeige4-2-3b",
+  "nex-n2-5-pro",
+  "olmo-2-1124-13b-instruct",
+  "ornith-1-5-35b-a3b",
+  "ornith-1-5-9b",
+  "phi-3-5-mini-instruct",
+  "phi-4",
+  "phi-4-mini-instruct",
+  "qwen-agentworld-35b-a3b",
+  "qwen2-5-0-5b-instruct",
+  "qwen2-5-1-5b-instruct",
+  "qwen2-5-14b-instruct",
+  "qwen2-5-32b-instruct",
+  "qwen2-5-3b-instruct",
+  "qwen2-5-72b-instruct",
+  "qwen2-5-7b-instruct",
+  "qwen2-5-coder-32b-instruct",
+  "qwen2-5-coder-7b-instruct",
+  "qwen3-0-6b",
+  "qwen3-1-7b",
+  "qwen3-14b",
+  "qwen3-30b-a3b",
+  "qwen3-32b",
+  "qwen3-4b",
+  "qwen3-8b",
+  "qwq-32b",
+  "qwythos-9b-claude-mythos-5-1m",
+  "smollm2-1-7b-instruct",
+  "smollm2-135m-instruct",
+  "smollm2-360m-instruct",
+  "spark-x2-5-4b",
+  "tinyllama-1-1b-chat-v1-0",
+  "yi-1-5-34b-chat"
+]
  2. 5 tool updates
    • First observedbiquadDesign
    • First observedllmVramFit
    • First observedroomModes
    • First observedroomShapeBand
    • First observedsolenoidField

Related MCP Connectors

Related MCP Servers

  • embedcalc-mcp

    ethan-hub26
    A
    license
    A
    quality
    B
    maintenance
    MCP server providing embedded engineering calculators and code generators as tools for AI agents, enabling precise, deterministic embedded math and C code generation.
    29
    47 npm
    MIT

  • lingshu-solver

    genesis-plan
    A
    license
    A
    quality
    A
    maintenance
    Enables deterministic solving of real-valued equation systems with up to six variables, providing certified solutions via interval contraction and Krawczyk verification, and honestly marking truncation when exhaustive search is incomplete—all offline with zero dependencies.
    2
    24 npm
    -

  • mathlas

    Archerkattri
    A
    license
    A
    quality
    A
    maintenance
    Airtight math tools an AI uses over MCP — 3.7M-theorem search, PSLQ constant ID, OEIS, real Lean kernel checks, applicability checklists. No LLM inside, no API key.
    12
    40 PyPI
    12
    Apache 2.0

  • chimeraforge

    Sahil170595
    A
    license
    A
    quality
    A
    maintenance
    LLM deployment planner: given a model and a GPU, answers will it fit, will it hit your SLO, and what will it cost. Sizes VRAM and KV-cache from the model's real architecture, and labels every number measured, estimated, or unknown.
    5
    277 PyPI
    2
    MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources