# io.github.farssaadeldin7-ux/predictive-resource-allocation (mcpb · predictive-resource-allocation.mcpb)

Predict where a render, simulation or training job will bottleneck, and what to change first.

- Trust score: 35/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- mcpb · `predictive-resource-allocation.mcpb`: 35/100 (this document), [markdown](https://verifymcp.io/servers/farssaadeldin7-ux-predictive-resource-allocation/predictive-resource-allocation.md), [page](https://verifymcp.io/servers/farssaadeldin7-ux-predictive-resource-allocation/predictive-resource-allocation)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/farssaadeldin7-ux/claude-plugin-suite/releases/download/mcpb-v0.1.3/predictive-resource-allocation.mcpb`
- Version: `0.1.3`
- Transport: `stdio`
- SHA-256: `a53e936f6a61606d8ca969684eebf8e7466260914072cb74a79a47d52f05f1d1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-23.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 2 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 79/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2402 tokens (~160/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 98% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

**Unverified: 2 categories.** Categories scored 0 because we could not verify them: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the io.github.farssaadeldin7-ux/predictive-resource-allocation MCP server?

io.github.farssaadeldin7-ux/predictive-resource-allocation ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, a53e936f6a61606d8ca969684eebf8e7466260914072cb74a79a47d52f05f1d1; the commands to do that are on this page. If it does not match, do not open it.

- Download bundle: `https://github.com/farssaadeldin7-ux/claude-plugin-suite/releases/download/mcpb-v0.1.3/predictive-resource-allocation.mcpb`
- SHA-256: `a53e936f6a61606d8ca969684eebf8e7466260914072cb74a79a47d52f05f1d1`

### Verify on macOS / Linux

```bash
echo "a53e936f6a61606d8ca969684eebf8e7466260914072cb74a79a47d52f05f1d1  predictive-resource-allocation.mcpb" | shasum -a 256 -c
```

### Verify on Windows (PowerShell)

```powershell
(Get-FileHash -Algorithm SHA256 .\predictive-resource-allocation.mcpb).Hash -eq "a53e936f6a61606d8ca969684eebf8e7466260914072cb74a79a47d52f05f1d1"
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-21 (score 35)

First indexed and scored.

## MCP tools (15)

### `triage_reference` (~105 tokens)

The four constraint classes (plus the two non-resource patterns), the four discriminating tests with their readings, the symptom index, the bandwidth ladder and the minimum intake the method demands before predicting. Reference data only — it names no class for your job; classify_bottleneck does that from measured readings. Omit section to get everything.

Input parameters:

- `section` (string): Optional single section: classes, tests, symptom_index, bandwidth_ladder, minimum_intake, rules_of_thumb.

### `domain_profile` (~111 tokens)

Per-application bottleneck profile: what usually binds, the governing scaling law, and the settings that move it most — for GPU path tracing (Cycles, Redshift, Octane), Houdini FLIP and Pyro, Nuke, After Effects and model training. Table data from the references, not advice about your scene. Omit domain to list all of them.

Input parameters:

- `domain` (string): path_tracing, houdini_flip, houdini_pyro, nuke, after_effects or training.

### `remedy_ladder` (~68 tokens)

The fixed remedy order — change a setting, change the data layout, change the algorithm, buy hardware — with typical cost and gain per rank, the four reasons hardware is last, and the one honest exception (the capacity cliff). Static reference; it does not rank remedies for a specific job.

### `vram_estimate` (~332 tokens)

GPU rendering capacity arithmetic against a card's usable budget (nominal minus the 10–15% reserve): geometry at 50–100 bytes per triangle, BVH at 1.3–2x geometry, textures with the 1.33x mip chain, framebuffer with AOVs, engine overhead. Returns the breakdown and a fits / thin / does_not_fit verdict with a plus-or-minus 20% band. Arithmetic over your reported scene only — it does not read the scene file and does not predict render time. Requires a paid plan.

Input parameters:

- `aov_count` (number): AOV / render pass count, for the framebuffer term.
- `bytes_per_triangle` (number): Reference range 50–100; default 64.
- `engine_overhead_gb` (number): Renderer and driver overhead in GB; default 1.5.
- `resolution` (object): Output resolution, for the framebuffer term.
- `subdivision_level` (number): Render-time subdivision level (each level is 4x the triangles). Default 0.
- `textures` (array): Texture sets: [{width_px, height_px, channels, bytes_per_channel, count}]. E.g. a 4K 8-bit RGB set is {width_px: 4096, height_px: 4096, channels: 3, bytes_per_channel: 1}.
- `triangles` (number, required): Unique (non-instanced) triangle count. Instanced copies are close to free.
- `vram_gb` (number, required): Nominal VRAM of the card, in GB.

### `training_memory_estimate` (~252 tokens)

Training capacity arithmetic: static state from the bytes-per-parameter table (16 for mixed precision with Adam, 10 for 8-bit Adam or SGD, LoRA and inference variants), transformer activations at layers x batch x seq x hidden x 34 bytes, against the card's usable budget. When static state alone exceeds the card it says so and lists the algorithmic remedies — lowering the batch size cannot fix that case. Arithmetic only; it does not predict step time or convergence. Requires a paid plan.

Input parameters:

- `activations` (object): Optional transformer activation inputs. Without them the total is static state only.
- `configuration` (string): One of: fp32_or_mixed_adam, mixed_sgd_or_8bit_adam, lora, inference_fp16. Default fp32_or_mixed_adam (16 bytes per parameter).
- `parameters_billion` (number, required): Model size in billions of parameters, e.g. 7 for a 7B model.
- `trainable_adapter_parameters_million` (number): LoRA only: trainable adapter parameters, in millions.
- `vram_gb` (number, required): Nominal VRAM of the card, in GB.

### `classify_bottleneck` (~204 tokens)

Apply the discriminating tests' thresholds to measured readings you supply — halve-the-work timings, VRAM occupancy against GPU utilisation, cold against warm cache, clock-scaling sensitivity — and count the agreement. Names a class only when two findings agree; otherwise it says insufficient or conflicting and which test would settle it. Threshold checks over your numbers, not a profiler — it measures nothing itself. Requires a paid plan.

Input parameters:

- `clock_scaling` (object): Test 4: throughput loss (percent) from a 10% memory clock cut and/or a 10% core clock cut.
- `cold_warm` (object): Test 3: the same job timed twice, unchanged.
- `halve_work` (object): Test 1: time one unit before and after halving batch size, tile size, resolution or samples.
- `occupancy_utilisation` (object): Test 2: VRAM occupancy and GPU utilisation read together, or a sawtoothing flag.

### `dispatch_plan` (~175 tokens)

Farm and cloud arithmetic from one measured frame time and one measured per-frame overhead: the 10x-overhead dispatch rule, the batching band, how the work type scales across nodes, and optionally the Young–Daly checkpoint interval for spot instances. It does not estimate cost or pick a provider. Requires a paid plan.

Input parameters:

- `frame_time_seconds` (number, required): Measured time per frame (or per task unit), in seconds.
- `overhead_seconds` (number, required): Measured per-frame fixed overhead — scene load, texture load, BVH build, licence checkout. Typically 30–120s.
- `spot` (object): Optional: include the Young–Daly checkpoint interval for spot / preemptible instances.
- `work_type` (string): One of: rendering, batch_comp, simulation, training. Default rendering.

### `system_snapshot` (~143 tokens)

Measured host telemetry from this machine, via Node built-ins and a probed nvidia-smi: total and free RAM (plus MemAvailable on Linux), logical cores and CPU model, 1/5/15-minute load averages (reported as unsupported on Windows rather than shown as zeros), platform and architecture, NVIDIA GPU name and memory when nvidia-smi answers — otherwise gpu is reported unavailable, never guessed, so AMD, Intel and Apple GPUs show as unavailable — and the top resident-memory processes on Linux. Every figure is measured; a snapshot is a point in time, not a profile over a job, and nothing leaves this machine. Requires a paid plan.

### `headroom_check` (~312 tokens)

Check an estimate against this machine's actual memory: takes a snapshot internally, runs the same arithmetic as vram_estimate or training_memory_estimate (pass the same inputs in the render or training block; vram_gb may be omitted when an NVIDIA card is measurable), and reports fits / thin / does_not_fit against the MEASURED free memory — free VRAM via nvidia-smi for resource gpu_vram, allocatable system RAM for resource system_ram — with the references' 10–15% reserve applied to the real number. When it does not fit, the machine's largest measured memory consumers are listed as the concrete background tasks to close. Every figure is labelled measured or estimated. Requires a paid plan.

Input parameters:

- `gpu_index` (number): Which measured GPU to check on a multi-card machine. Default 0.
- `job` (string, required): Which estimator to run: render (vram_estimate's arithmetic) or training (training_memory_estimate's).
- `render` (object): For job "render": the same inputs vram_estimate takes. vram_gb is optional here — when omitted, the measured card's total is used.
- `resource` (string, required): Which measured resource to check against: gpu_vram (needs nvidia-smi) or system_ram.
- `training` (object): For job "training": the same inputs training_memory_estimate takes. vram_gb is optional here — when omitted, the measured card's total is used.

### `estimate_log` (~277 tokens)

The local estimate log that closes the loop: log a prediction (action "log"), record the measured actual against it once the job has run (action "record_actual"), or review the tally of how past estimates landed against the stated factor-of-two band (action "review"). Counting only — the review makes no new claim. Requires a paid plan. Nothing leaves this machine.

Input parameters:

- `action` (string, required): log, record_actual or review.
- `actual_value` (number): record_actual: the measured value, same unit as predicted.
- `assumptions` (string): log: the assumptions behind the estimate, so a miss can be traced to one.
- `estimate_id` (string): record_actual: the id returned by a previous log.
- `job` (string): log: what the estimate is for, e.g. "shot 040 4K render".
- `limit` (number): review: how many recent estimates to list. Default 20.
- `notes` (string)
- `predicted_value` (number): log: the estimate, as a positive number.
- `quantity` (string): log: what is being estimated, e.g. vram_gb, frame_time_seconds, sim_time_hours.
- `unit` (string): log: the unit of predicted_value, e.g. "GB", "seconds".

### `license_status` (~51 tokens)

Check the Predictive Resource Allocation licence on this machine: plan, included capabilities, remaining quota and seat usage. Call this when a paid tool reports a licence problem, or when the user asks what their plan includes.

### `license_activate` (~68 tokens)

Store and activate a Predictive Resource Allocation licence key on this machine. Use when the user pastes a licence key, or after a purchase completes.

Input parameters:

- `license_key` (string, required): The licence key, e.g. PS-XXX-00000-00000-00000-0000

### `start_checkout` (~75 tokens)

Begin a Predictive Resource Allocation purchase. Returns a Stripe Checkout link. Call list_plans first if the user has not chosen a plan.

Input parameters:

- `email` (string): Email address for the receipt and licence.
- `plan` (string, required): Plan id: "pro" or "team". Use list_plans to see the options.

### `list_plans` (~25 tokens)

List the available Predictive Resource Allocation plans, prices and what each one includes.

### `billing_portal` (~31 tokens)

Open the Stripe billing portal to change plan, update the card, or cancel the Predictive Resource Allocation subscription.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/farssaadeldin7-ux-predictive-resource-allocation/predictive-resource-allocation#diagnostics

## Score history

- 2026-10-23: 35
- 2026-10-22: 35
- 2026-10-21: 35

## Common questions

### What is the io.github.farssaadeldin7-ux/predictive-resource-allocation MCP server?

io.github.farssaadeldin7-ux/predictive-resource-allocation is an MCP server listed in the public MCP registry as io.github.farssaadeldin7-ux/predictive-resource-allocation. Predict where a render, simulation or training job will bottleneck, and what to change first. This page covers its MCPB bundle (https://github.com/farssaadeldin7-ux/claude-plugin-suite/releases/download/mcpb-v0.1.3/predictive-resource-allocation.m…).

### Is the io.github.farssaadeldin7-ux/predictive-resource-allocation MCP server safe to use?

io.github.farssaadeldin7-ux/predictive-resource-allocation scores 35 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.farssaadeldin7-ux/predictive-resource-allocation MCP server expose?

io.github.farssaadeldin7-ux/predictive-resource-allocation exposes 15 tools: triage_reference, domain_profile, remedy_ladder, vram_estimate, training_memory_estimate, and 10 more. Their descriptions and schemas cost roughly 2,229 tokens of context every time the server is loaded.

## Links

- Repository: https://github.com/farssaadeldin7-ux/claude-plugin-suite
- Changelog RSS feed: https://verifymcp.io/servers/farssaadeldin7-ux-predictive-resource-allocation/predictive-resource-allocation.xml
- Changelog JSON feed: https://verifymcp.io/servers/farssaadeldin7-ux-predictive-resource-allocation/predictive-resource-allocation.json
- HTML version of this page: https://verifymcp.io/servers/farssaadeldin7-ux-predictive-resource-allocation/predictive-resource-allocation