Install @runapi.ai/mcp from npm
Install exact version 0.12.2. No verified executable entrypoint is available, so use the package documentation to launch it.
npm install --save-exact @runapi.ai/mcp@0.12.2MCP server intelligence profile
RunAPI MCP Server
Connects MCP-compatible coding tools to RunAPI for AI image, video, music, text-to-speech, and LLM generation using 130+ models from leading providers
1Distribution channel
9Independently observed tools
0Linked remote endpoints
AvailableVersion intelligence
Install and connect
Installation and connection instructions are shown only when supported by retained package, repository, or endpoint evidence.
Identity
| Canonical slug | runapi-mcp-server-4b45aa05 | Deployment | Local Only |
|---|---|---|---|
| Canonical package | npm:@runapi.ai/mcp | Repository | runapi-ai/mcp |
| First published | Aug 12, 2026 | Latest release | Aug 12, 2026 |
| Last security verification | — | Classification confidence | 90% |
| Publication | Published | Official distribution | Yes |
Distributions
| Channel | Identifier | Current version | Versions | Source |
|---|---|---|---|---|
| npm | @runapi.ai/mcp | 0.12.2 | 38 | Repository |
Current release
| Package | Version | Published / observed | Inventory | Security scan |
|---|---|---|---|---|
| npm@runapi.ai/mcp | 0.12.2Current | Sep 5, 2026 | 9 toolsSucceeded · 0 resources · 0 prompts | Failed |
Enterprise protection
Continuously monitor this MCP for security risk
Independently scan the exact version your agents use, receive alerts when its risk changes, and investigate every finding with retained version evidence.
- Independent exact-version security scans
- Continuous release and vulnerability monitoring
- Risk-change alerts with capability context
- Historical evidence and API exports
Custom pricingContact salesTailored to your organization, integrations, data needs, and support requirements.
Current version evidence
| Provenance | artifact_hash_verified | Signature | — |
|---|---|---|---|
| MCP SDK | — | Artifact SHA-256 | 91dba061609973c405614fe3b421038922da31d63b31e8f346a2213ae2d94515 |
| Scanner | mcp-proof-engine 0.1.0 | Scan completed | Sep 4, 2026 |
| Security rating | — | Methodology | — |
Current protocol inventory
2025-06-18Negotiated protocol
@runapi.ai/mcpServer-reported name
2Capability groups
Sep 4, 2026Observed
Tools 9
| Tool | Category | Annotations | Risk |
|---|---|---|---|
check_balanceReturn the authenticated RunAPI account balance and spending metrics.Input schema{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {}
} | — | — | |
check_pricingReturn current runtime pricing for a RunAPI model/action pair.Input schema{
"type": "object",
"properties": {
"service": {
"type": "string",
"description": "RunAPI service slug returned by list_models"
},
"action": {
"type": "string",
"description": "RunAPI endpoint name, for example text_to_image or text_to_music"
},
"model": {
"type": "string",
"description": "RunAPI model slug"
}
},
"required": [
"service",
"action"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — | |
create_taskRun a RunAPI operation with a caller-generated idempotency key. Asynchronous operations can optionally poll until completion.Input schema{
"type": "object",
"properties": {
"service": {
"type": "string",
"description": "RunAPI service slug returned by list_models"
},
"action": {
"type": "string",
"description": "RunAPI endpoint name, for example text_to_image"
},
"model": {
"type": "string",
"description": "RunAPI model slug"
},
"params": {
"type": "object",
"additionalProperties": {},
"default": {},
"description": "Endpoint parameters validated against data/contract.json where constrained."
},
"idempotency_key": {
"type": "string",
"minLength": 1,
"maxLength": 512,
"description": "Opaque caller-generated key for safely replaying one logical task creation."
},
"wait": {
"type": "boolean",
"default": true,
"description": "Wait for the completed result when the endpoint requires durable processing."
},
"timeout_ms": {
"type": "integer",
"exclusiveMinimum": 0,
"description": "Requested completion deadline in milliseconds; values above the endpoint limit are capped."
},
"poll_interval_ms": {
"type": "integer",
"exclusiveMinimum": 0,
"description": "Status check interval while waiting for completion."
}
},
"required": [
"service",
"action",
"idempotency_key"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — | |
get_model_infoGet supported endpoint, current runtime pricing, and input constraints for a RunAPI model slug. Add service and action when the model supports multiple endpoints.Input schema{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "RunAPI model slug returned by list_models"
},
"service": {
"type": "string",
"description": "RunAPI service slug returned by list_models; use with action to disambiguate multi-endpoint models"
},
"action": {
"type": "string",
"description": "RunAPI endpoint name returned by list_models; use with service to disambiguate multi-endpoint models"
}
},
"required": [
"model"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — | |
get_taskFetch the current status and latest payload for an existing RunAPI task.Input schema{
"type": "object",
"properties": {
"service": {
"type": "string"
},
"action": {
"type": "string",
"description": "RunAPI endpoint name. Provide this when using media task routes."
},
"task_id": {
"type": "string"
}
},
"required": [
"service",
"task_id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — | |
list_actionsList RunAPI endpoint names grouped by output modality.Input schema{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {}
} | — | — | |
list_modelsList RunAPI models from the embedded catalog. Optional filters: modality, service, or action.Input schema{
"type": "object",
"properties": {
"modality": {
"type": "string",
"enum": [
"image",
"video",
"audio",
"utility"
]
},
"service": {
"type": "string"
},
"action": {
"type": "string"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — | |
loginAuthenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json.Input schema{
"type": "object",
"properties": {
"force": {
"type": "boolean",
"default": false,
"description": "Re-run browser login when the current credential comes from the local config file."
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — | |
search_promptsSearch RunAPI prompt examples by modality, category, tags, text query, model, or featured status. Free, no API key required.Input schema{
"type": "object",
"properties": {
"modality": {
"type": "string",
"enum": [
"image",
"image_edit",
"video",
"audio",
"music"
]
},
"category": {
"type": "string"
},
"tags": {
"type": "array",
"items": {
"type": "string"
},
"description": "Tags to match. All provided tags must be present."
},
"q": {
"type": "string",
"description": "Text query matched against prompt title and prompt text."
},
"model": {
"type": "string",
"description": "RunAPI model slug, for example flux-kontext-pro or suno-v5."
},
"featured": {
"type": "boolean"
},
"page": {
"type": "integer",
"exclusiveMinimum": 0
},
"per_page": {
"type": "integer",
"exclusiveMinimum": 0,
"maximum": 100
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
} | — | — |
Resources 0
- None observed.
Resource templates 0
- None observed.
Prompts 0
- None observed.
Remote endpoints
| Endpoint | Transport | Authentication | Health | Observed |
|---|---|---|---|---|
| No verified remote endpoint is linked. | ||||
RunAPI MCP Server questions
How do I install RunAPI MCP Server?
Install the selected package version with: npm install --save-exact @runapi.ai/mcp@0.12.2
What tools does RunAPI MCP Server provide?
RunAPI MCP Server exposed 9 tools during independent protocol observation, including check_balance, check_pricing, create_task, get_model_info, get_task, list_actions, list_models, login, and others.
Is RunAPI MCP Server secure?
Our scanner tested version 0.12.2 without proving a finding in the methods exercised. This is not a guarantee that every deployment is secure.
Explore related MCP server guides
Curated product and capability guides containing this catalog record.