AgentCompute MCP server
io.github.Ockram4444/agentcomputeOckram4444streamable-httpv0.11.0Scanned
Shared GPU beta: account API/MCP, task catalog, text, images and audio. Capacity varies.
11 tools: 5 change things and 6 only read.
- Reads private data · 1
- Reads text others write · 2
- Can send data out · 0
- 8 findings
Tools listed without sign-in. Remote posture
With Anlyon
5 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the AgentCompute MCP server can do
The AgentCompute MCP server is published by the GitHub account Ockram4444. It has 11 tools. It can create or change data (5 tools: submit_catalog_job, submit_agent_job, submit_compute_job, submit_chat_job and 1 more), but cannot delete data. 6 tools only read.
1 tool reads private data (get_studio_job); 2 tools bring in text other people can write (submit_agent_job and get_studio_job).
The fixed checks matched 8 findings (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 11, 2026, version 0.11.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
11 tools
Changes things 5Claude Code: ask
submit_agent_jobExperimental local worker agent.Reads text others write1 finding
Why it is in this group
- The name "submit_agent_job" says "submit": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The input schema at properties.access_token.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.access_token.description: "Account API credential from My account; omit when Bearer autho..."
Description, as the server wrote it 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 bytes total). Set required_artifacts to exact filenames to require delivery. Version 3 requires services.agent_web and adds public HTTPS page reading and web search, with source URLs. No JavaScript browsing, logins, VM, arbitrary code or shell. Search availability and website access can vary. File contents are returned in result.agent_result.artifacts. Quotes are matched; tool outputs and factual correctness are not independently verified. Account authentication, concurrency and per-job limits apply. Poll get_studio_job.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
submit_catalog_jobExperimental structured extraction from one to six nonconfidential product records supplied as text.1 finding
Why it is in this group
- The name "submit_catalog_job" says "submit": a word for a change.
Findings
- Info
The input schema at properties.access_token.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.access_token.description: "Account API credential from My account; omit when Bearer autho..."
Description, as the server wrote it Experimental structured extraction from one to six nonconfidential product records supplied as text. No URL fetching or OCR. Check catalog_extraction.available first. One task unit, bounded retries; retain idempotency_key. Output includes JSON/CSV with source quotes and null for missing data. Schema and source matching are checked, semantic correctness is not guaranteed. Poll get_studio_job.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
submit_chat_jobDefault routing fairly rotates compatible idle providers.1 finding
Why it is in this group
- The name "submit_chat_job" says "submit": a word for a change.
Findings
- Info
The input schema at properties.access_token.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.access_token.description: "Account credential from My account; optional with Bearer a..."
Description, as the server wrote it Default routing fairly rotates compatible idle providers. Optional parallel:{parts:2|3,objective,documents} splits document analysis and returns one synthesized result under the same job ID. Each part and synthesis count toward quotas. Otherwise provide messages. Routing fastest requires comparable configured benchmarks; lowest_cost uses configured prices, with fair fallback when metrics are unknown. No payment. 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
submit_compute_jobBeta users must supply their uploaded asset_id and kind compute_job.1 finding
Why it is in this group
- The name "submit_compute_job" says "submit": a word for a change.
Findings
- Info
The input schema at properties.access_token.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.access_token.description: "Account credential created in My account. Optional when Be..."
Description, as the server wrote it 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 idempotency_key for retries, and use a new key only for a new job.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
submit_image_jobQueue a free text-to-image task from a complete scene description.1 finding
Why it is in this group
- The name "submit_image_job" says "submit": a word for a change.
Findings
- Info
The input schema at properties.access_token.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.access_token.description: "Account credential from My account; optional with Bearer a..."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 6Show 6 read-only tools
get_capability_catalogRead the common published-service catalog, accepted output types, account requirement, submission/result tools and per-service live status paths.No findings
Why it is in this group
- The name "get_capability_catalog" says "get": a word for reading.
Description, as the server wrote it Read the common published-service catalog, accepted output types, account requirement, submission/result tools and per-service live status paths. This is not a live availability claim. Experimental candidates are excluded. Check status before submission.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_compute_jobRead a previously submitted job by job_id.1 finding
Why it is in this group
- The name "get_compute_job" says "get": a word for reading.
Findings
- Info
The input schema at properties.access_token.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.access_token.description: "Account credential from My account; optional with Bearer a..."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_compute_statusCheck prepared audio-provider and queue capacity.No findings
Why it is in this group
- The name "get_compute_status" says "get": a word for reading.
Description, as the server wrote it Check prepared audio-provider and queue capacity. Languages and the exact profile are returned; audio availability is separate from Studio. Account daily limits are absent; anonymous-demo eligibility is reported separately. Returns availability, permitted task types, and limits. Does not start a job.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_service_statusPublic live availability, model catalog, separate account and anonymous-demo limits and polling guidance.No findings
Why it is in this group
- The name "get_service_status" says "get": a word for reading.
Description, as the server wrote it Public live availability, model catalog, separate account and anonymous-demo limits and polling guidance. No token required. Check before submitting; an offline GPU cannot execute work.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_studio_imageReturn the completed image as an MCP image content block.1 finding
Why it is in this group
- The name "get_studio_image" says "get": a word for reading.
Findings
- Info
The input schema at properties.access_token.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.access_token.description: "Account API credential from My account; omit when Bearer autho..."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_studio_jobRead your own chat, image, agent, catalog or coordinated-analysis job.Reads private dataReads text others write1 finding
Why it is in this group
- The name "get_studio_job" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "chat": it reads messages.
- untrusted-inputThe description's first sentence says "read" and "chat": it reads messages, which other people can write.
Findings
- Info
The input schema at properties.access_token.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.access_token.description: "Account API credential from My account; omit when Bearer autho..."
Description, as the server wrote it Read your own chat, image, agent, catalog or coordinated-analysis 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 15, 2026, 13:22 UTC, unchanged since Oct 31, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 5
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcp: tools/list returned 11 tools to an anonymous client, including submit_catalog_job (write), submit_agent_job (write), submit_compute_job (write), submit_chat_job (write), submit_image_job (write)
Posture changes
- Oct 31, 2026
- Tools that change things, listed without credentials: 4 to 5
Findings
Matches of fixed checks, with the text they matched.
The input schema at properties.access_token.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.access_token.description: "Account API credential from My account; omit when Bearer autho..."
- Infosubmit_agent_job
The input schema at properties.access_token.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.access_token.description: "Account API credential from My account; omit when Bearer autho..."
The input schema at properties.access_token.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.access_token.description: "Account credential created in My account. Optional when Be..."
- Infoget_compute_job
The input schema at properties.access_token.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.access_token.description: "Account credential from My account; optional with Bearer a..."
- Infosubmit_chat_job
The input schema at properties.access_token.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.access_token.description: "Account credential from My account; optional with Bearer a..."
- Infosubmit_image_job
The input schema at properties.access_token.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.access_token.description: "Account credential from My account; optional with Bearer a..."
Show 2 more findingsShow fewer
- Infoget_studio_job
The input schema at properties.access_token.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.access_token.description: "Account API credential from My account; omit when Bearer autho..."
- Infoget_studio_image
The input schema at properties.access_token.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.access_token.description: "Account API credential from My account; omit when Bearer autho..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 added, 1 removed, 9 changed.+2 added−1 removed~9 changedView diff
- Added:get_capability_catalogOnly reads
- Added:submit_catalog_jobChanges things
- Removed:create_trial_access
- Changed:get_compute_jobOnly readsinputSchema
- Changed:get_compute_statusOnly readsdescription
- Changed:get_service_statusOnly readsdescription
- Changed:get_studio_imageOnly readsinputSchema
- Changed:get_studio_jobOnly readstitledescriptioninputSchema
- Changed:submit_agent_jobChanges thingsdescriptioninputSchemaannotations
- Changed:submit_chat_jobChanges thingsinputSchema
- Changed:submit_compute_jobChanges thingsinputSchema
- Changed:submit_image_jobChanges thingsinputSchema
Tools1 added, 2 changed.+1 added~2 changedView diff
- Added:submit_agent_jobChanges things
- Changed:create_trial_accessChanges thingsdescription
- Changed:submit_chat_jobChanges thingsdescriptioninputSchema
PostureRemote posture changed. Tools that change things, listed without credentials: 4 -> 5.View diff
- Tools that change things, listed without credentials: 4 to 5
Install
Pinned to version 0.11.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agentcompute https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcpclaude mcp add --transport http agentcompute https://u8x5gpk0ul.execute-api.eu-north-1.amazonaws.com/v1/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__agentcompute__get_capability_catalog",
"mcp__agentcompute__get_compute_status",
"mcp__agentcompute__get_compute_job",
"mcp__agentcompute__get_service_status",
"mcp__agentcompute__get_studio_job",
"mcp__agentcompute__get_studio_image"
],
"ask": [
"mcp__agentcompute__submit_catalog_job",
"mcp__agentcompute__submit_agent_job",
"mcp__agentcompute__submit_compute_job",
"mcp__agentcompute__submit_chat_job",
"mcp__agentcompute__submit_image_job"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agentcompute. Review it before you use it.
Capability tags behind 2 rules
- mcp__agentcompute__submit_agent_job untrusted-input
- mcp__agentcompute__get_studio_job private-data, untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.Ockram4444/agentcompute/verify?hash=de3ed5978979898715bf08e55173187a112570fffbad43262e3ad30fc87a505a" | jq -e '.changed == false'Pinned hash de3ed5978979, from Nov 11, 2026, 10:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Ockram4444/agentcompute/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Ockram4444/agentcompute)Source: MCP Registry. Synced Nov 11, 2026, 10:17 UTC.
AgentCompute MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the AgentCompute MCP server safe?
- No scan can promise that. What its definitions show: 11 tools, 5 of which can change, send or delete something, and 8 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the AgentCompute MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the AgentCompute MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the AgentCompute MCP server have?
- 11 tools: 5 write, 6 read. submit_catalog_job, submit_agent_job, submit_compute_job, submit_chat_job, submit_image_job, get_capability_catalog, get_compute_status, get_compute_job and 3 more.
Does the AgentCompute MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the AgentCompute MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the AgentCompute MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 11, 2026. Every change is on this page and in its Atom feed.