MCP server that wraps the Dagster GraphQL API — manage runs, assets, schedules, sensors, and backfills from any MCP client
Nothing to run from here
AgentCompute is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
10
tools declared
remote
at its publisher
—
calls last 7d
What it does
Free experimental GPU tools: text generation, images and audio transcription. Shared quotas; no SLA.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http agentcompute-mcp https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcp
# 2 — ask your agent for something these tools do
# submit_agent_job, create_trial_access, get_compute_status and 7 more
AgentCompute costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
OCAll 1 server
Ockram44441 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http agentcompute-mcp https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
10 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Experimental local worker agent. Version 1 reads supplied documents. Set agent_task.version=2 for decimal calculations, CSV preview/filter/numeric sort/summary/group sums, and TXT/Markdown/CSV/JSON files using approved local CPU/RAM functions. Check services.agent_tools for version 2. Up to eight tool calls, eight optional documents, 24000 input characters and three files (16000 bytes each, 24000
| Parameter | Type | Required | Notes |
|---|---|---|---|
| access_token | string | no | — |
| agent_task | object | yes | — |
| consent | boolean | yes | — |
| idempotency_key | string | yes | — |
Create a private 24-hour trial token automatically. No ChatGPT account, payment or manual setup. Audio: 3 jobs per session. Chat/images: 72 total submissions per rolling 24 hours, 10 per session/reported client, one active task per session, shared queue of 3. Global access issuance caps apply. Retain the token for upload and result retrieval. Reuse the session; never create new sessions to bypass
No parameter schema on file.
Check whether the GPU provider can accept audio transcription work. Returns availability, permitted task types, and limits. Does not start a job.
No parameter schema on file.
Beta users must supply their uploaded asset_id and kind compute_job. No accuracy guarantee is made for uploaded files. Owner legacy calls can queue the fixed synthetic benchmark. compute_job returns a transcript; delegated_task additionally requires word error rate at most 10% against the known reference. Returns a job_id to poll with get_compute_job. No payment is charged. Reuse the same idempote
| Parameter | Type | Required | Notes |
|---|---|---|---|
| access_token | string | no | Temporary token returned by create_trial_access. Optional when Bearer authentication is configured. |
| asset_id | string | no | Owned upload ID returned by POST /v1/beta/upload. Required for public beta buyers. |
| kind | string | yes | Transcription only, or transcription with the reference quality gate. |
| idempotency_key | string | yes | Unique request key. Keep it unchanged on retries. |
Read a previously submitted job by job_id. Returns status, transcript, runtime and reference quality when complete. For queued or running jobs, wait poll_after_seconds before checking again. Failed or expired jobs are not successful results.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| access_token | string | no | Temporary trial token, unless Bearer authentication is configured. |
| job_id | string | yes | Exact job_id returned by submit_compute_job. |
Public live availability, model catalog, free-trial limits and polling guidance. No token required. Check before submitting; an offline GPU cannot execute work.
No parameter schema on file.
Queue a free text task: draft, summarize, extract, translate text, reason or assist with code. No code is executed. Provide user/assistant messages, explicit consent for nonconfidential permitted content, and a stable idempotency key. Returns immediately with a job ID. Poll get_studio_job. Uses the configured local model, no external AI fallback.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| access_token | string | no | Private token from create_trial_access; optional with Bearer authentication. |
| messages | array | yes | At most 12,000 characters in total. End with a user message. Include previous messages for follow-up context. |
| consent | boolean | yes | Confirm permission to process this nonconfidential content. |
| idempotency_key | string | yes | — |
Queue a free text-to-image task from a complete scene description. Each task is independent, not an edit of a previous image. Returns a job ID; poll get_studio_job then get_studio_image for the PNG. Configured model and size appear in service status/results. No external AI fallback.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| access_token | string | no | Private token from create_trial_access; optional with Bearer authentication. |
| prompt | string | yes | Complete image description. English prompts are recommended. |
| consent | boolean | yes | Confirm permission to process this nonconfidential content. |
| idempotency_key | string | yes | — |
Read your own chat/image job. Includes partial text while running, final text or image availability, GPU runtime and server timings. Wait poll_after_seconds between checks; stop on succeeded, failed or expired. Does not create or retry work.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| access_token | string | no | — |
| job_id | string | yes | — |
Return the completed image as an MCP image content block. Requires the same token/identity that submitted the job. Images expire after 24 hours from submission; download before expiry.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| access_token | string | no | — |
| job_id | string | yes | — |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install AgentCompute or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 0.8.0 · scanned 28 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 0 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest0eda3bb3edc29414efeedb6dc8716fb963d9eb91272c628980654aa072a757c7
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| submit_agent_job | untrusted-inputstate-write | untrusted-input: keyword "web_search"; state-write: declares readOnlyHint: false |
| create_trial_access | state-write | state-write: declares readOnlyHint: false |
| get_compute_status | no tags | |
| submit_compute_job | state-write | state-write: declares readOnlyHint: false |
| get_compute_job | no tags | |
| get_service_status | no tags | |
| submit_chat_job | state-write | state-write: declares readOnlyHint: false |
| submit_image_job | state-write | state-write: declares readOnlyHint: false |
| get_studio_job | no tags | |
| get_studio_image | untrusted-input | untrusted-input: keyword "download" |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest0eda3bb3edc29414
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.8.0.
0.8.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish AgentCompute can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.