What can you do with this server?

The Jungle Grid MCP Server is a gateway that lets AI agents submit, monitor, and manage GPU workloads on Jungle Grid's cloud infrastructure. Key capabilities include: * Estimate a job (estimate_job) — Get a cost and GPU tier estimate before committing, with options to compare optimization strategies (cost, speed, balanced). * Submit a job (submit_job) — Launch a GPU workload asynchronously using a Docker image and command, with configuration options for GPU type/class, region, environment variables, disk size, latency/cost priority, and Hugging Face credentials. * Get job status (get_job) — Retrieve the current status and full details of a specific job; terminal states are completed, failed, and cancelled. * List jobs (list_jobs) — Retrieve a paginated list of recent jobs, optionally filtered by status. * Cancel a job (cancel_job) — Cancel a pending, queued, or running job with an optional reason. * Get job logs (get_job_logs) — Retrieve stdout/stderr output for a completed or running job. * Stream job logs (stream_job_logs) — Stream live log output in real-time, blocking until the job reaches a terminal state or a timeout (up to 10 minutes). * List job artifacts (list_job_artifacts) — List output artifacts uploaded from /workspace/artifacts for managed jobs. * Get artifact download URL (get_artifact_download_url) — Generate a temporary signed download URL for a specific job artifact.

de en es ja ko ru zh

jungle-grid-mcp-server

Official

by Jungle-Grid

Overview Schema Source Related Servers Score Discussions(1)Admin

TypeScript

Remote

Jungle Grid MCP Server

Jungle Grid MCP lets MCP-aware agents estimate, submit, monitor, cancel, and retrieve artifacts from Jungle Grid workloads. It supports local stdio clients and hosted Streamable HTTP deployments that forward tool calls to the Jungle Grid API.

Use it for asynchronous AI workload execution, batch processing, training, fine-tuning, uploaded file or script backed jobs, lifecycle diagnostics, workload logs, and managed output artifacts.

Installation

Requirements:

Node.js 18 or newer
A Jungle Grid API key for local stdio, or an OAuth bearer token for hosted HTTP
API scopes that match the tools you want to call

Run the local stdio server with npx:

JUNGLE_GRID_API_KEY=jg_placeholder npx -y @jungle-grid/mcp

Install globally if you prefer a stable executable:

npm install -g @jungle-grid/mcp
junglegrid-mcp

Related MCP server: clausius

Configuration

Local stdio uses environment variables:

Variable	Required	Purpose
`JUNGLE_GRID_API_KEY`	Yes for local stdio	Bearer token forwarded to the Jungle Grid API.
`JUNGLEGRID_API_BASE`	No	API base URL. Defaults to `https://api.junglegrid.dev`.
`JUNGLE_GRID_API_URL`	No	Legacy API base URL alias, also accepted.

Hosted HTTP gateway deployments also support:

Variable	Required	Purpose
`MCP_TRANSPORT=http`	No	Starts Streamable HTTP instead of stdio.
`PORT`	No	HTTP port. Defaults to `3000`.
`JUNGLEGRID_INTERNAL_SERVICE_TOKEN`	No	Service token used for OAuth introspection or fallback API calls.
`OAUTH_ISSUER`	No	OAuth issuer. Defaults to `https://api.junglegrid.dev`.
`MCP_RESOURCE`	No	Protected resource URL. Defaults to `https://mcp.junglegrid.dev`.
`MCP_RESOURCE_METADATA_URL`	No	OAuth protected-resource metadata URL.
`OPENAI_APPS_CHALLENGE_TOKEN`	No	Enables `/.well-known/openai-apps-challenge` when configured.

Never commit API keys, OAuth tokens, signed upload URLs, signed artifact URLs, or callback secrets.

Connection Modes

Local stdio

Local clients launch the package and communicate over stdio.

{
  "mcpServers": {
    "junglegrid": {
      "command": "npx",
      "args": ["-y", "@jungle-grid/mcp"],
      "env": {
        "JUNGLE_GRID_API_KEY": "jg_placeholder"
      }
    }
  }
}

Claude Desktop

Add the same mcpServers block to claude_desktop_config.json, then fully quit and reopen Claude Desktop.

macOS:

~/Library/Application Support/Claude/claude_desktop_config.json

Windows:

%APPDATA%\Claude\claude_desktop_config.json

Cursor

For project config, avoid checked-in secrets. Put the key in the environment used to launch Cursor:

{
  "mcpServers": {
    "junglegrid": {
      "command": "npx",
      "args": ["-y", "@jungle-grid/mcp"]
    }
  }
}

For a local uncommitted Cursor config:

{
  "mcpServers": {
    "junglegrid": {
      "command": "npx",
      "args": ["-y", "@jungle-grid/mcp"],
      "env": {
        "JUNGLE_GRID_API_KEY": "jg_placeholder",
        "JUNGLEGRID_API_BASE": "https://api.junglegrid.dev"
      }
    }
  }
}

Hosted HTTP

The HTTP server exposes:

GET /healthz
GET /.well-known/oauth-protected-resource
POST /mcp

Start it locally:

MCP_TRANSPORT=http PORT=3000 JUNGLEGRID_INTERNAL_SERVICE_TOKEN=service_token_placeholder npm start

Hosted MCP clients must send Authorization: Bearer <oauth_access_token> to POST /mcp. The server introspects tokens at /oauth/introspect on the configured API base and requires tool-specific scopes.

Minimal Working Example

Ask your MCP client to call the tools in this order:

{
  "tool": "estimate_job",
  "arguments": {
    "workload_type": "batch",
    "image": "python:3.11-slim",
    "command": ["python", "-c", "print('hello from Jungle Grid')"],
    "routing_mode": "balanced"
  }
}

If the estimate is acceptable, submit the job:

{
  "tool": "submit_job",
  "arguments": {
    "name": "mcp-hello",
    "workload_type": "batch",
    "image": "python:3.11-slim",
    "command": ["python", "-c", "print('hello from Jungle Grid')"],
    "expected_artifacts": ["/workspace/artifacts/output.txt"]
  }
}

Use the returned job_id with get_job, get_job_events, get_job_logs, list_artifacts, and get_artifact.

MCP Tools

The current tool registry exposes these exact tool names:

Tool	Purpose	Required parameters	Optional parameters
`estimate_job`	Estimate routing, capacity source, and expected cost without creating work.	`workload_type`	`model_size`, `image`, `command`, `args`, `routing_mode`, `template`, `notes`
`submit_job`	Submit a workload. This may start compute and incur usage charges.	`name`, `workload_type`, `image`	`model_size`, `command`, `args`, `env`, `input_files`, `script_files`, `script_file`, `expected_artifacts`, `routing_mode`, `template`, `metadata`
`upload_job_input`	Create a signed upload slot for an input file or script.	`filename`	`content_type`, `kind`
`list_job_inputs`	List uploaded inputs and scripts for the authenticated account.	none	none
`list_jobs`	List recent jobs.	none	`limit`, `cursor`, `status`
`get_job`	Read job status, phase, scheduling, billing, and artifact readiness.	`job_id`	none
`get_job_events`	Read lifecycle events for scheduling, provisioning, startup, failures, and cancellation.	`job_id`	none
`get_job_logs`	Read persisted runtime and workload logs.	`job_id`	`limit`, `cursor`
`cancel_job`	Request cancellation of a non-terminal job.	`job_id`	`reason`
`list_artifacts`	List managed output artifacts for a job.	`job_id`	none
`get_artifact`	Create temporary artifact download information.	`job_id`, `artifact_id`	none

Accepted workload_type values are inference, training, fine_tuning, and batch. The MCP server forwards fine_tuning to the REST API as fine-tuning. Accepted routing_mode values are cost, speed, and balanced.

Tool Details

`estimate_job`

Returns classification, route status, capacity source, estimated cost range, availability, and screening details when returned by the API. An estimate is not a reservation and does not guarantee immediate startup.

Common errors: missing workload_type, invalid enum value, authentication failure, forbidden scope, invalid request, upstream API error.

{
  "workload_type": "inference",
  "model_size": 7,
  "image": "pytorch/pytorch:2.4.0-cuda12.1-cudnn9-runtime",
  "command": ["python", "infer.py"],
  "routing_mode": "balanced",
  "notes": "single model inference run"
}

`submit_job`

Creates an asynchronous job. model_size is an optional size in GB used to select suitable GPU capacity and is forwarded as REST model_size_gb. command is preferably an array of strings. env must be an object with string values and is forwarded as REST environment. input_files and script_files accept arrays of { "input_id": "..." }; string IDs are normalized for compatibility. The current REST implementation supports one uploaded script reference.

Expected response includes job_id, status, queued_at or submitted_at, routing fields, input/script details, and artifact contract fields when returned by the API.

Common errors: missing name, image, or workload_type; invalid workload type; command or args too long; invalid environment values; missing or incomplete input IDs; insufficient funds; unavailable capacity; maintenance; authentication or scope failures.

{
  "name": "transcribe-audio",
  "workload_type": "inference",
  "model_size": 7,
  "image": "python:3.11-slim",
  "command": ["python", "/workspace/scripts/transcribe.py", "/workspace/inputs/audio.ogg", "/workspace/artifacts/transcript.txt"],
  "script_files": [{ "input_id": "inp_script123" }],
  "input_files": [{ "input_id": "inp_audio123" }],
  "expected_artifacts": ["/workspace/artifacts/transcript.txt"],
  "routing_mode": "balanced",
  "metadata": {
    "request_id": "req_123"
  }
}

`upload_job_input`

Creates a signed upload slot. It does not upload file bytes by itself. Upload the bytes to upload.upload_url using upload.method, then complete the upload with upload.complete_url and the returned upload.token.

kind is an arbitrary string accepted by the API. Use input for normal input files and script for scripts by convention. Script uploads mount under /workspace/scripts/<filename>; input uploads mount under /workspace/inputs/<filename>.

Expected response:

{
  "upload": {
    "input_id": "inp_123",
    "filename": "transcribe.py",
    "method": "PUT",
    "upload_url": "https://signed-upload.example",
    "token": "upload_token",
    "expires_at": "2026-06-11T12:15:00Z",
    "complete_url": "https://api.junglegrid.dev/v1/job-inputs/inp_123/complete"
  }
}

Common errors: missing filename, invalid filename, file too large, upload storage unavailable, authentication or scope failure.

`list_job_inputs`

Returns uploaded inputs with input_id, filename, content_type, size_bytes, kind, status, ready, mount_path, and timestamps when available.

`list_jobs`

Returns jobs, limit, next_cursor, and has_more. limit is capped by the API. status is a free-form filter string passed to the API; do not assume the MCP schema restricts it to a fixed enum.

`get_job`

Returns the current job status and details. Status, execution phase, lifecycle events, runtime details, and workload logs are separate surfaces.

Important response fields include status, phase, execution_phase, status_message, status_reason, phase_started_at, phase_last_updated_at, wait_duration_seconds, delayed_start, delay_reason, scheduling, startup_diagnostics, provider, artifacts_ready, failure, input_files, script_file, and artifact_contract when present.

`get_job_events`

Returns lifecycle events before and during execution. Events may exist before workload logs begin. Events include IDs, types, phases, titles, messages, source, level, timestamps, sequence, and a generated timestamp.

Use events to diagnose queueing, route selection, scheduling, provider provisioning, input preparation, startup, retries, failures, and cancellation.

`get_job_logs`

Returns stored log entries with items, next_cursor, has_more, failure_highlight, and usage_hint when available. Entries include entry_id, source, category, stream, message, truncated, and created_at when returned by the API.

Logs can be empty while a job is queued, scheduling, provisioning, or preparing. Call get_job_events when logs are empty but the job is not terminal. This MCP tool fetches persisted logs; it does not provide true streaming.

`cancel_job`

Requests cancellation for a pending, queued, assigned, starting, or running job. Completed, failed, rejected, or already cancelled jobs return a conflict from the API.

Expected response includes job_id, status, and status_reason when returned by the API. Cancellation may trigger managed teardown, but do not assume immediate infrastructure shutdown.

`list_artifacts`

Returns managed artifacts for a job. Artifacts include artifact_id, job_id, filename, content_type, size_bytes, status, ready, and timestamps when returned by the API. Failed jobs may have no artifacts or partial artifacts.

`get_artifact`

Creates temporary download information for one artifact. The API returns artifact metadata, a signed URL, and expires_at. Treat the URL as a secret.

Common errors: artifact not found, artifact not ready, artifact storage unavailable, forbidden job, authentication failure.

Production Workflows

Simple Job

Estimate:

{
  "workload_type": "batch",
  "image": "python:3.11-slim",
  "command": ["python", "-c", "from pathlib import Path; Path('/workspace/artifacts/output.txt').write_text('done')"],
  "routing_mode": "balanced"
}

Submit:

{
  "name": "simple-artifact-job",
  "workload_type": "batch",
  "image": "python:3.11-slim",
  "command": ["python", "-c", "from pathlib import Path; Path('/workspace/artifacts/output.txt').write_text('done')"],
  "expected_artifacts": ["/workspace/artifacts/output.txt"],
  "routing_mode": "balanced"
}

Monitor:

{ "job_id": "job_123" }

Call get_job, get_job_events, and get_job_logs with the same job_id until the status is terminal.

Retrieve:

{ "job_id": "job_123" }

Call list_artifacts, then:

{
  "job_id": "job_123",
  "artifact_id": "art_123"
}

File-Backed Job

Create upload slots:

{
  "filename": "transcribe.py",
  "content_type": "text/x-python",
  "kind": "script"
}

{
  "filename": "audio.ogg",
  "content_type": "audio/ogg",
  "kind": "input"
}

Upload each file to the returned signed upload_url, then complete it:

curl -X PUT "$UPLOAD_URL" \
  -H "Content-Type: text/x-python" \
  --data-binary @transcribe.py

curl -X POST "$COMPLETE_URL" \
  -H "Authorization: Bearer $JUNGLE_GRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "token": "upload_token",
    "filename": "transcribe.py",
    "content_type": "text/x-python",
    "size_bytes": 1234,
    "etag": "optional-etag"
  }'

Submit with input IDs:

{
  "name": "file-backed-transcription",
  "workload_type": "inference",
  "image": "python:3.11-slim",
  "command": ["python", "/workspace/scripts/transcribe.py", "/workspace/inputs/audio.ogg", "/workspace/artifacts/transcript.txt"],
  "script_files": [{ "input_id": "inp_script123" }],
  "input_files": [{ "input_id": "inp_audio123" }],
  "expected_artifacts": ["/workspace/artifacts/transcript.txt"]
}

Monitor with get_job_events, get_job, and get_job_logs.
Retrieve /workspace/artifacts/transcript.txt with list_artifacts and get_artifact.

Error Shape

REST MCP routes return an envelope:

{
  "ok": false,
  "error": {
    "code": "INVALID_REQUEST",
    "message": "name, image, and workload_type are required"
  }
}

The MCP server converts API errors into tool errors like:

submit_job failed: INVALID_REQUEST: name, image, and workload_type are required

Common API codes include UNAUTHORIZED, FORBIDDEN, INVALID_REQUEST, JOB_INPUT_NOT_FOUND, JOB_INPUT_NOT_READY, ARTIFACT_NOT_READY, NOT_FOUND, CONFLICT, INSUFFICIENT_FUNDS, MAINTENANCE_ACTIVE, and INTERNAL_ERROR.

Security

Keep API keys and OAuth tokens out of prompts, source control, browser bundles, logs, and issue trackers.
Prefer host secret stores or local-only MCP config files for JUNGLE_GRID_API_KEY.
Treat signed upload and artifact URLs as temporary bearer secrets.
Do not print environment variables that contain tokens from workload code.
Review submit_job and cancel_job requests before allowing an agent to execute them, because they can spend credits or stop active work.

Development

npm install
npm run build
npm test

Run stdio from the built package:

JUNGLE_GRID_API_KEY=jg_placeholder node dist/index.js

Run HTTP locally:

MCP_TRANSPORT=http PORT=3000 JUNGLEGRID_INTERNAL_SERVICE_TOKEN=service_token_placeholder node dist/index.js

Inspect with MCP Inspector:

JUNGLE_GRID_API_KEY=jg_placeholder npx @modelcontextprotocol/inspector node dist/index.js

Full Documentation

Public Jungle Grid documentation: https://junglegrid.dev/docs

MCP documentation page: https://junglegrid.dev/docs/mcp

License

MIT

Available Tools

8 tools

cancel_jobA

Destructive

Cancel an existing Jungle Grid job. This may stop active execution and prevent further outputs.

ParametersJSON Schema

Name	Required	Description	Default
`jobId`	Yes
`reason`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`data`	Yes

TDQS

A4/5.0

Behavior4/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false; the description goes further by stating the concrete behavioral effects: stopping active execution and preventing further outputs. This adds context not captured by the annotations and is consistent with them.

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?

Two sentences, the action is front-loaded, and every word adds meaning. No unnecessary detail or redundancy.

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

Completeness3/5

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

For a simple two-parameter mutation with an output schema, the core purpose and behavior are covered. However, the meaning of the reason parameter is missing, and there is no guidance on edge cases like cancelling an already-completed job. This leaves a moderate gap for an AI agent.

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

Parameters2/5

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

The schema has 0% description coverage, and the description does not explain either parameter. jobId is only implied by 'existing job,' and the optional reason parameter is entirely unexplained. Agents must infer parameter meaning without support.

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 uses a specific verb and resource: 'Cancel an existing Jungle Grid job,' which clearly distinguishes it from sibling tools like submit_job, get_job, and list_jobs. It also adds the functional effect of stopping active execution and preventing further outputs, leaving no ambiguity about the tool's purpose.

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 provides clear usage context: it applies to an existing job and may affect active execution. It does not explicitly name alternatives or when-not conditions, but no sibling tool offers cancellation, so the context is sufficient for an agent to select this tool.

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

estimate_jobA

Read-only

Estimate routing, capacity source, and expected cost for a proposed Jungle Grid workload without submitting it.

ParametersJSON Schema

Name	Required	Description
`workload`	Yes
`model_size`	No	Optional model size in GB.
`image`	No
`command`	No
`args`	No
`routing_mode`	No
`template`	No
`notes`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`data`	Yes

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description need not reiterate safety. It adds value by specifying what the estimate covers (routing, capacity, cost). No contradictions with annotations. However, it omits details like rate limits or state effects, but these are less critical for a read-only estimate.

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 a single, well-structured sentence with no filler. It front-loads the key action and resource, making it easy to process. Every word contributes to understanding.

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

Completeness3/5

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

Given 8 parameters (1 required) and an output schema, the description covers the tool's purpose but lacks parameter guidance. The complexity is moderate, and while the output schema reduces the need to explain return values, the missing parameter semantics leave the description incomplete for correct invocation.

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

Parameters2/5

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

Schema description coverage is only 13% (only model_size described). The tool description does not elaborate on how parameters like workload, routing_mode, image, command, etc., affect the estimate. With low coverage, the description should compensate but fails to add meaningful parameter context, leaving parameters ambiguous.

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 clearly states the action ('Estimate'), the resource ('Jungle Grid workload'), and the specific aspects estimated ('routing, capacity source, expected cost'). It also distinguishes itself from submission tools by noting 'without submitting it', making the purpose very specific.

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 implies when to use this tool (before submission) versus the sibling 'submit_job'. However, it does not explicitly exclude cases like checking existing jobs or provide alternative contexts. While clear for its primary use case, additional guidance on when not to use it would improve this dimension.

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

get_artifactA

Read-only

Retrieve download information for a specific output artifact from a Jungle Grid job.

ParametersJSON Schema

Name	Required	Description	Default
`jobId`	Yes
`artifactId`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`data`	Yes

TDQS

A3.7/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is known. The description adds the distinction that this provides download information rather than artifact content, but it reveals little else about behavior.

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?

A single, direct sentence that front-loads the action and resource. There is no filler or redundant repetition of the tool name.

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

Completeness4/5

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

For a simple read-only getter with an output schema, the description adequately covers the core purpose. It falls short only in not explicitly guiding the agent toward when to prefer list_artifacts, but this is a minor gap given the tool's simplicity.

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

Parameters2/5

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

Schema description coverage is 0%, so the description carries the burden of explaining parameters. It only loosely maps 'job' and 'specific artifact' to jobId and artifactId, but adds no format, constraints, or additional meaning for either parameter.

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 states a specific action ('Retrieve download information') and a specific resource ('a specific output artifact from a Jungle Grid job'). It clearly differs from siblings like list_artifacts and get_job.

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 description implies when to use it: when download information for a particular artifact is needed. However, it does not explicitly contrast with alternatives such as list_artifacts or mention any exclusions.

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

get_jobA

Read-only

Retrieve current status and execution details for a specific Jungle Grid job belonging to the authenticated user.

ParametersJSON Schema

Name	Required	Description	Default
`jobId`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`data`	Yes

TDQS

A3.9/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds 'belonging to the authenticated user' (auth constraint) and specifies 'status and execution details' as return content. No contradiction, but marginal additional value.

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?

One sentence with clear verb-object structure, no filler, directly conveys essential information.

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?

Output schema exists, so return values are documented externally. Description covers purpose and auth constraint. Annotations provide safety profile. Complete for a simple read operation.

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 coverage is 0%, but the single parameter jobId is self-explanatory given its name and the tool's purpose. The description does not add extra detail about jobId format or constraints, but baseline 3 is appropriate for a simple, clear parameter.

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 clearly specifies the verb 'Retrieve' and the resource 'specific Jungle Grid job', distinguishing it from siblings like list_jobs (list all) and cancel_job (cancel). It also adds scope 'belonging to the authenticated user'.

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 description implies use for retrieving a specific job's status/details, but lacks explicit guidance on when to use vs alternatives (e.g., when to use get_job vs get_job_logs or list_jobs). No when-not-to-use conditions.

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

get_job_logsB

Read-only

Retrieve execution logs for a specific Jungle Grid job belonging to the authenticated user.

ParametersJSON Schema

Name	Required	Description	Default
`jobId`	Yes
`limit`	No
`cursor`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`data`	Yes

TDQS

B3/5.0

Behavior3/5

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

Annotations already mark this as read-only and non-destructive. The description adds the user-scoping constraint, which is valuable behavioral context. However, it does not disclose pagination behavior (despite the 'cursor' parameter), potential rate limits, or the fact that logs may be truncated. With annotations covering safety, this is adequate but not rich.

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?

A single, perfectly scoped sentence that conveys the core action and resource. No extraneous information. Ideal conciseness.

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

Completeness2/5

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

Given the tool has three parameters (one required) and an output schema exists, the description should cover parameter semantics and usage context. It fails on parameter explanation and provides no usage guidelines. The output schema likely covers return structure, but the description's gaps make the tool incomplete for an agent.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must explain parameters. Only 'jobId' is implicitly clear from the resource name. The optional parameters 'limit' and 'cursor' are not mentioned, leaving their semantics entirely unspecified. This is a significant gap that hampers correct invocation.

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?

Description clearly states the verb 'Retrieve' and the resource 'execution logs for a specific Jungle Grid job'. It adds a key constraint ('belonging to the authenticated user') that helps distinguish from potential admin-only tools. However, it does not explicitly differentiate from sibling tools like 'get_job' or 'get_artifact', preventing a perfect score.

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?

No guidance is provided on when to use this tool versus alternatives such as 'list_jobs' or 'get_job'. There is no mention of prerequisites, context, or any exclusion criteria, leaving the agent to infer usage solely from the tool name and description.

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

list_artifactsA

Read-only

List output artifacts associated with a specific Jungle Grid job.

ParametersJSON Schema

Name	Required	Description	Default
`jobId`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`data`	Yes

TDQS

A4/5.0

Behavior3/5

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

The annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds job-scoped output artifact context, but does not disclose additional behavioral details such as pagination, ordering, or empty-result behavior.

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 a single sentence with no filler. The core action and scope are front-loaded, making it easy for an agent to parse quickly.

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

Completeness4/5

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

For a simple read-only list tool with one parameter, an output schema, and safety annotations, the description is largely sufficient. It could be more complete by pointing to get_artifact for retrieving a single artifact, but that is optional rather than essential.

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 0%, so the description must compensate. It maps jobId to 'a specific Jungle Grid job,' which provides the core semantic, but it does not give format details, examples, or how to obtain the job ID.

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 uses a specific verb and resource: 'List output artifacts associated with a specific Jungle Grid job.' This clearly identifies the operation and distinguishes it from sibling tools like list_job_inputs (inputs) and get_artifact (single artifact).

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 phrase 'associated with a specific Jungle Grid job' provides clear context for when to use the tool: when you need output artifacts for a known job. It does not explicitly name alternatives or exclusions, so it stops short of a 5.

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

list_jobsA

Read-only

List the authenticated user's Jungle Grid jobs, optionally filtered by status. Use this to find recent jobs before checking status, logs, or artifacts.

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No
`cursor`	No
`status`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`data`	Yes

TDQS

A3.9/5.0

Behavior3/5

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

Annotations already declare the tool readOnly and non-destructive, so the safety profile is covered. The description adds useful scope information ('authenticated user's jobs') and implies recency ordering, but it does not go into pagination or response behavior. No contradiction with annotations.

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?

Two short sentences, with the core action front-loaded and the usage guidance second. Every sentence earns its place and there is no filler or repetition of schema information.

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

Completeness4/5

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

The description conveys the tool's purpose, user scope, optional filtering, and its place in the job workflow. With an output schema available, return structure does not need to be spelled out. It only lacks explicit pagination semantics and accepted status values, which are conventional gaps rather than deal-breakers.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate for parameter meaning. It only addresses 'status' as a filter and leaves 'limit' and 'cursor' entirely unexplained, with no status value details. This is inadequate for a tool with three undocumented optional parameters.

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 states a specific verb ('List'), a clearly bounded resource ('the authenticated user's Jungle Grid jobs'), and an optional filter ('by status'). It is readily distinguishable from sibling tools like get_job, which targets a single job, and list_artifacts/list_job_inputs, which target different resources.

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 explicitly guides when to use it: 'Use this to find recent jobs before checking status, logs, or artifacts.' This gives an agent a clear workflow trigger. It does not name alternatives or state when not to use it, but the contextual cue is strong enough.

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

submit_jobA

Submit a Jungle Grid workload for execution. This may start managed compute infrastructure and incur usage charges.

ParametersJSON Schema

Name	Required	Description	Default
`name`	Yes
`workload`	Yes
`image`	Yes
`command`	No
`args`	No
`env`	No
`routing_mode`	No
`template`	No
`metadata`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`data`	Yes

TDQS

A3.5/5.0

Behavior4/5

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

Annotations already indicate non-read-only and non-destructive. The description adds important behavioral context: starting infrastructure and incurring charges, which goes beyond the annotations.

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?

Two focused sentences with no redundancy. Every word adds value.

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

Completeness2/5

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

Despite having an output schema and 9 parameters, the description provides minimal context. It lacks parameter guidance, error handling, or return value details, making it insufficient for a complex submission tool.

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

Parameters1/5

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

Schema has 0% description coverage for 9 parameters. The description does not explain any parameter's meaning or usage, leaving the agent to infer from names alone.

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 explicitly states the action ('Submit') and the resource ('Jungle Grid workload for execution'), clearly distinguishing it from siblings like cancel_job or get_job.

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 description hints at when to use (for submission) and warns about potential charges and infrastructure startup, but does not explicitly compare to alternatives or state when not to use.

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.

11 tool updatesv0.1.9Jun 3, 2026

Changedcancel_job5 fields changed

addedInput schema / properties / jobId
```
Added value: +{
+  "type": "string"
+}
```

removedInput schema / properties / job_id

Removed value: -{
-  "description": "The ID of the job to cancel.",
-  "type": "string"
-}

removedInput schema / properties / reason / description
```
Removed value: -"Optional cancellation reason."
```

changedInput schema / required

Previous value: -[
-  "job_id"
-]New value: +[
+  "jobId"
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "data": {
+      "additionalProperties": true,
+      "properties": {
+        "cancelled": {
+          "type": "boolean"
+        },
+        "id": {
+          "type": "string"
+        },
+        "job_id": {
+          "type": "string"
+        },
+        "message": {
+          "type": "string"
+        },
+        "status": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    }
+  },
+  "required": [
+    "data"
+  ],
+  "type": "object"
+}

Changedestimate_job20 fields changed

addedInput schema / properties / args

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / command
```
Added value: +{
+  "type": "string"
+}
```

removedInput schema / properties / cost_priority

Removed value: -{
-  "enum": [
-    "low",
-    "balanced",
-    "high"
-  ],
-  "type": "string"
-}

removedInput schema / properties / disk_gb

Removed value: -{
-  "description": "Optional managed-provider local disk override in GB. Leave unset to let Jungle Grid auto-size from model_size_gb.",
-  "type": "number"
-}

removedInput schema / properties / gpu_class

Removed value: -{
-  "enum": [
-    "consumer",
-    "datacenter"
-  ],
-  "type": "string"
-}

removedInput schema / properties / gpu_type

Removed value: -{
-  "enum": [
-    "A100",
-    "A10G",
-    "H100",
-    "L4",
-    "RTX3090",
-    "RTX4090",
-    "RTX5090",
-    "T4"
-  ],
-  "type": "string"
-}

removedInput schema / properties / image / description
```
Removed value: -"Docker image to run."
```

removedInput schema / properties / latency_priority

Removed value: -{
-  "enum": [
-    "low",
-    "balanced",
-    "high"
-  ],
-  "type": "string"
-}

addedInput schema / properties / model_size

Added value: +{
+  "description": "Optional model size in GB.",
+  "type": "number"
+}

removedInput schema / properties / model_size_gb

Removed value: -{
-  "description": "Approximate model size in GB — drives tier selection.",
-  "type": "number"
-}

addedInput schema / properties / notes
```
Added value: +{
+  "type": "string"
+}
```

removedInput schema / properties / optimize_for

Removed value: -{
-  "enum": [
-    "balanced",
-    "cost",
-    "speed"
-  ],
-  "type": "string"
-}

removedInput schema / properties / region_mode

Removed value: -{
-  "enum": [
-    "prefer",
-    "strict"
-  ],
-  "type": "string"
-}

removedInput schema / properties / region_preference
```
Removed value: -{
-  "type": "string"
-}
```

addedInput schema / properties / routing_mode

Added value: +{
+  "enum": [
+    "cost",
+    "speed",
+    "balanced"
+  ],
+  "type": "string"
+}

addedInput schema / properties / template
```
Added value: +{
+  "type": "string"
+}
```

addedInput schema / properties / workload

Added value: +{
+  "enum": [
+    "inference",
+    "training",
+    "fine_tuning",
+    "batch"
+  ],
+  "type": "string"
+}

removedInput schema / properties / workload_type

Removed value: -{
-  "enum": [
-    "inference",
-    "training",
-    "fine-tuning",
-    "batch"
-  ],
-  "type": "string"
-}

changedInput schema / required

Previous value: -[
-  "workload_type",
-  "image"
-]New value: +[
+  "workload"
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "data": {
+      "additionalProperties": true,
+      "properties": {
+        "available": {
+          "type": "boolean"
+        },
+        "can_submit": {
+          "type": "boolean"
+        },
+        "capacity": {
+          "additionalProperties": true,
+          "properties": {
+            "estimate_source": {
+              "type": "string"
+            },
+            "live_candidate_count": {
+              "type": "number"
+            },
+            "live_capacity_available": {
+              "type": "boolean"
+            },
+            "managed_capacity_available": {
+              "anyOf": [
+                {
+                  "type": "boolean"
+                },
+                {
+                  "type": "null"
+                }
+              ]
+            },
+            "managed_profile_count": {
+              "type": "number"
+            }
+          },
+          "type": "object"
+        },
+        "classification": {
+          "additionalProperties": true,
+          "properties": {
+            "acceleration_requirement": {
+              "type": "string"
+            },
+            "confidence": {
+              "type": "string"
+            },
+            "reasons": {
+              "items": {
+                "type": "string"
+              },
+              "type": "array"
+            },
+            "requires_gpu": {
+              "type": "boolean"
+            },
+            "workload_type": {
+              "type": "string"
+            }
+          },
+          "type": "object"
+        },
+        "estimated_cost_max_usd": {
+          "type": "number"
+        },
+        "estimated_cost_min_usd": {
+          "type": "number"
+        },
+        "estimated_cost_usd": {
+          "additionalProperties": true,
+          "properties": {
+            "max": {
+              "type": "number"
+            },
+            "min": {
+              "type": "number"
+            }
+          },
+          "required": [
+            "min",
+            "max"
+          ],
+          "type": "object"
+        },
+        "likely_gpu_type": {
+          "type": "string"
+        },
+        "routed_gpu_tier": {
+          "type": "string"
+        },
+        "routing": {
+          "additionalProperties": true,
+          "properties": {
+            "route_status": {
+              "type": "string"
+            },
+            "selected_accelerator": {
+              "type": "string"
+            },
+            "selected_route_source": {
+              "type": "string"
+            },
+            "selection_reason": {
+              "type": "string"
+            }
+          },
+          "type": "object"
+        },
+        "screening": {}
+      },
+      "type": "object"
+    }
+  },
+  "required": [
+    "data"
+  ],
+  "type": "object"
+}

Addedget_artifact
Removedget_artifact_download_url

Changedget_job4 fields changed

addedInput schema / properties / jobId
```
Added value: +{
+  "type": "string"
+}
```

removedInput schema / properties / job_id

Removed value: -{
-  "description": "The job ID returned by submit_job.",
-  "type": "string"
-}

changedInput schema / required

Previous value: -[
-  "job_id"
-]New value: +[
+  "jobId"
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "data": {
+      "additionalProperties": true,
+      "properties": {
+        "account_billing": {
+          "additionalProperties": true,
+          "properties": {
+            "lifetime_total_spent_usd": {
+              "type": "number"
+            }
+          },
+          "type": "object"
+        },
+        "actual_cost_usd": {
+          "anyOf": [
+            {
+              "type": "number"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "artifacts_ready": {
+          "type": "boolean"
+        },
+        "estimated_cost_usd": {
+          "additionalProperties": true,
+          "properties": {
+            "max": {
+              "type": "number"
+            },
+            "min": {
+              "type": "number"
+            }
+          },
+          "required": [
+            "min",
+            "max"
+          ],
+          "type": "object"
+        },
+        "id": {
+          "type": "string"
+        },
+        "job_id": {
+          "type": "string"
+        },
+        "last_status_update": {
+          "type": "string"
+        },
+        "phase": {
+          "type": "string"
+        },
+        "status": {
+          "type": "string"
+        },
+        "status_message": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    }
+  },
+  "required": [
+    "data"
+  ],
+  "type": "object"
+}

Changedget_job_logs6 fields changed

addedInput schema / properties / cursor
```
Added value: +{
+  "type": "string"
+}
```
addedInput schema / properties / jobId
```
Added value: +{
+  "type": "string"
+}
```

removedInput schema / properties / job_id

Removed value: -{
-  "description": "The job ID to fetch logs for.",
-  "type": "string"
-}

addedInput schema / properties / limit
```
Added value: +{
+  "type": "number"
+}
```

changedInput schema / required

Previous value: -[
-  "job_id"
-]New value: +[
+  "jobId"
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "data": {
+      "additionalProperties": true,
+      "properties": {
+        "items": {
+          "items": {
+            "additionalProperties": true,
+            "properties": {
+              "level": {
+                "type": "string"
+              },
+              "message": {
+                "type": "string"
+              },
+              "timestamp": {
+                "type": "string"
+              }
+            },
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "job_id": {
+          "type": "string"
+        },
+        "logs": {
+          "items": {
+            "additionalProperties": true,
+            "properties": {
+              "level": {
+                "type": "string"
+              },
+              "message": {
+                "type": "string"
+              },
+              "timestamp": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "message"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "next_cursor": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        }
+      },
+      "type": "object"
+    }
+  },
+  "required": [
+    "data"
+  ],
+  "type": "object"
+}

Addedlist_artifacts
Removedlist_job_artifacts

Changedlist_jobs6 fields changed

addedInput schema / properties / cursor
```
Added value: +{
+  "type": "string"
+}
```
addedInput schema / properties / limit / default
```
Added value: +10
```

removedInput schema / properties / limit / description

Removed value: -"Maximum number of jobs to return (default 20, max 100)."

removedInput schema / properties / status / description
```
Removed value: -"Filter by job status."
```

removedInput schema / properties / status / enum

Removed value: -[
-  "pending",
-  "queued",
-  "running",
-  "completed",
-  "failed",
-  "cancelled"
-]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "data": {
+      "additionalProperties": true,
+      "properties": {
+        "has_more": {
+          "type": "boolean"
+        },
+        "jobs": {
+          "items": {
+            "additionalProperties": true,
+            "properties": {
+              "created_at": {
+                "type": "string"
+              },
+              "id": {
+                "type": "string"
+              },
+              "job_id": {
+                "type": "string"
+              },
+              "name": {
+                "type": "string"
+              },
+              "status": {
+                "type": "string"
+              },
+              "updated_at": {
+                "type": "string"
+              },
+              "workload_type": {
+                "type": "string"
+              }
+            },
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "limit": {
+          "type": "number"
+        },
+        "next_cursor": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        }
+      },
+      "type": "object"
+    }
+  },
+  "required": [
+    "data"
+  ],
+  "type": "object"
+}

Removedstream_job_logs

Changedsubmit_job26 fields changed

addedInput schema / properties / args

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

removedInput schema / properties / command / description

Removed value: -"Container entrypoint arguments (e.g. ['python', 'train.py', '--epochs', '10'])."

removedInput schema / properties / command / items
```
Removed value: -{
-  "type": "string"
-}
```
changedInput schema / properties / command / type
```
Previous value: -"array"New value: +"string"
```

removedInput schema / properties / cost_priority

Removed value: -{
-  "description": "Cost sensitivity.",
-  "enum": [
-    "low",
-    "balanced",
-    "high"
-  ],
-  "type": "string"
-}

removedInput schema / properties / disk_gb

Removed value: -{
-  "description": "Optional managed-provider local disk override in GB. Leave unset to let Jungle Grid auto-size from model_size_gb.",
-  "type": "number"
-}

addedInput schema / properties / env

Added value: +{
+  "additionalProperties": {
+    "type": "string"
+  },
+  "type": "object"
+}

removedInput schema / properties / environment

Removed value: -{
-  "additionalProperties": {
-    "type": "string"
-  },
-  "description": "Environment variables injected into the container. Use this for large inline scripts such as CODE when you want to keep the command array short.",
-  "type": "object"
-}

removedInput schema / properties / gpu_class

Removed value: -{
-  "description": "Optional soft GPU class preference.",
-  "enum": [
-    "consumer",
-    "datacenter"
-  ],
-  "type": "string"
-}

removedInput schema / properties / gpu_type

Removed value: -{
-  "description": "Optional exact GPU override.",
-  "enum": [
-    "A100",
-    "A10G",
-    "H100",
-    "L4",
-    "RTX3090",
-    "RTX4090",
-    "RTX5090",
-    "T4"
-  ],
-  "type": "string"
-}

removedInput schema / properties / huggingface_credential_id

Removed value: -{
-  "description": "Optional saved Hugging Face credential to inject into the managed runtime. Falls back to your account default when omitted.",
-  "type": "string"
-}

removedInput schema / properties / image / description

Removed value: -"Docker image to run (e.g. 'pytorch/pytorch:2.2.0-cuda12.1-cudnn8-runtime')."

removedInput schema / properties / latency_priority

Removed value: -{
-  "description": "Latency sensitivity. Use 'high' for real-time inference.",
-  "enum": [
-    "low",
-    "balanced",
-    "high"
-  ],
-  "type": "string"
-}

addedInput schema / properties / metadata
```
Added value: +{
+  "type": "object"
+}
```

removedInput schema / properties / model_size_gb

Removed value: -{
-  "description": "Approximate model size in GB. Used to select the right GPU tier for inference jobs.",
-  "type": "number"
-}

removedInput schema / properties / name / description

Removed value: -"Optional readable job name. A name is generated if omitted."

removedInput schema / properties / optimize_for

Removed value: -{
-  "description": "Scheduling optimization goal. 'speed' prioritises latency; 'cost' minimises spend.",
-  "enum": [
-    "balanced",
-    "cost",
-    "speed"
-  ],
-  "type": "string"
-}

removedInput schema / properties / region_mode

Removed value: -{
-  "description": "Region preference mode.",
-  "enum": [
-    "prefer",
-    "strict"
-  ],
-  "type": "string"
-}

removedInput schema / properties / region_preference

Removed value: -{
-  "description": "Optional preferred region such as us-east or eu-west.",
-  "type": "string"
-}

addedInput schema / properties / routing_mode

Added value: +{
+  "enum": [
+    "cost",
+    "speed",
+    "balanced"
+  ],
+  "type": "string"
+}

addedInput schema / properties / template
```
Added value: +{
+  "type": "string"
+}
```

removedInput schema / properties / webhook_url

Removed value: -{
-  "description": "Optional HTTPS URL to receive signed lifecycle event callbacks.",
-  "type": "string"
-}

addedInput schema / properties / workload

Added value: +{
+  "enum": [
+    "inference",
+    "training",
+    "fine_tuning",
+    "batch"
+  ],
+  "type": "string"
+}

removedInput schema / properties / workload_type

Removed value: -{
-  "description": "Type of GPU workload.",
-  "enum": [
-    "inference",
-    "training",
-    "fine-tuning",
-    "batch"
-  ],
-  "type": "string"
-}

changedInput schema / required

Previous value: -[
-  "workload_type",
-  "image",
-  "command"
-]New value: +[
+  "name",
+  "workload",
+  "image"
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "data": {
+      "additionalProperties": true,
+      "properties": {
+        "estimated_cost_usd": {
+          "additionalProperties": true,
+          "properties": {
+            "max": {
+              "type": "number"
+            },
+            "min": {
+              "type": "number"
+            }
+          },
+          "required": [
+            "min",
+            "max"
+          ],
+          "type": "object"
+        },
+        "id": {
+          "type": "string"
+        },
+        "job_id": {
+          "type": "string"
+        },
+        "status": {
+          "type": "string"
+        },
+        "status_message": {
+          "type": "string"
+        },
+        "submitted_at": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    }
+  },
+  "required": [
+    "data"
+  ],
+  "type": "object"
+}

9 tool updatesv0.1.0May 10, 2026
- First observedcancel_job
- First observedestimate_job
- First observedget_artifact_download_url
- First observedget_job
- First observedget_job_logs
- First observedlist_job_artifacts
- First observedlist_jobs
- First observedstream_job_logs
- First observedsubmit_job

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.8/5.0

Scored 2026-06-03 02:02 across 8 tools

Disambiguation5/5

Each tool targets a distinct operation (submit, cancel, estimate, get status, get logs, list, get artifact, list artifacts) with no overlap. The separation between job management and artifact management is clear.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern using snake_case (e.g., cancel_job, get_artifact, list_jobs). The naming is predictable and easy to understand.

Tool Count5/5

With 8 tools, the server provides a focused but complete set for managing Jungle Grid jobs. Each tool serves a necessary function without bloat or undersupply.

Completeness4/5

Covers the core job lifecycle (submit, get, list, cancel, estimate, logs, artifacts). Missing an update/retry tool for modifying job parameters, but the core workflow is well-supported.

Maintenance

ActivityMaintained

ResponsivenessUnresponsive

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Hive Compute A
io.github.srotzin
HiveCompute MCP Server — decentralized inference router for AI agents
Agent Orchestration AI & Machine Learning
2
anotherai
dev.anotherai
MCP server for building and testing AI agents with multi-model experimentation and insights.
Agent Orchestration Autonomous Agents Testing & QA Tools
2
mcp A
com.everstake
MCP server connecting AI agents to non-custodial staking data across 130+ networks.
Blockchain Cryptocurrency
1111
Tigris MCP ServerOAuth
dev.storage
Tigris MCP Server seamlessly connects AI agents to Tigris bucket and object management.
Cloud Storage Cloud Platforms File Systems
2

Related MCP Servers

Modal MCP Server
Cloud Platforms Agent Orchestration Code Execution
smehmood
A
license
A
quality
D
maintenance
An MCP server that enables AI agents to interact with Modal, allowing them to deploy apps and run functions in a serverless cloud environment.
Updated a year ago (2025-03-25 22:53 UTC)
7
3
MIT
clausius
Monitoring Observability Command Line
tamohannes
F
license
Not graded
quality
A
maintenance
An MCP server for monitoring and managing multi-cluster Slurm GPU jobs, enabling AI agents to execute commands, check allocations, and explore logs across HPC clusters.
Updated a month ago (2026-07-30 00:35 UTC)
1
-
spiderswitch
AI & Machine Learning Agent Orchestration
hiddenpath
A
license
Not graded
quality
B
maintenance
MCP server that enables agents to dynamically switch between multiple AI models (OpenAI, Anthropic, Google, etc.) with unified protocol-driven configuration and capability discovery.
Updated 2 months ago (2026-07-07 15:53 UTC)
Apache 2.0
lab-ops
AceIke
A
license
Not graded
quality
C
maintenance
MCP server that converts SSH operations on training servers into AI-callable tools for GPU monitoring, job submission, file transfer, and more.
Updated 2 months ago (2026-07-19 12:23 UTC)
1
MIT