AIR MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AIR_API_KEY | Yes | Your AIR API key for authentication. |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tasks | {
"requests": {
"tools": {
"call": {}
}
}
} |
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| air_list_domainsA | List domains visible to the API key. For domain-scoped service account keys, returns the single bound domain. Requires domains:read scope. |
| air_get_domainA | Resolve a domain by pid from air_list_domains results, or by orgSlug + domainSlug via slug lookup. |
| air_list_projectsA | List projects in a domain (paginated). Requires domains:read and projects:read. Use domainPid from air_list_domains. |
| air_get_projectA | Resolve a project by pid from air_list_projects, or by orgSlug + domainSlug + projectSlug. |
| air_create_projectA | Create a project in a domain. Requires domains:write (fullPipeline preset). Returns project pid and slug. |
| air_searchA | Full-text search across orgs, domains, and projects. Requires search:read scope (fullPipeline preset; not included in assessmentRunner). |
| air_list_documentsA | List document sources for a project. Poll until status is connected before starting an assessment. Requires projects:read. |
| air_get_document_download_urlA | Get a presigned download URL for an uploaded document source. Requires projects:read. |
| air_list_artifactsA | List document-derived artifacts for a project. Use artifact pids in air_start_assessment. Requires projects:read. |
| air_get_artifact_textA | Get extracted plain text for an artifact. Requires projects:read. |
| air_upload_document_initA | Start presigned upload: returns uploadUrl and s3Key. PUT file bytes to uploadUrl, then call air_upload_document_complete. Requires projects:write. |
| air_upload_document_completeA | Finalize presigned upload after PUT to uploadUrl. Dispatches document extraction workflow. Requires projects:write. |
| air_list_assessmentsC | List assessment summaries for a project. Requires assessments:read. |
| air_get_assessmentA | Get assessment detail including status and workflowRunId. Requires assessments:read. |
| air_get_assessment_reportB | Fetch the structured risk assessment report JSON for a completed run. Requires assessments:read. |
| air_get_assessment_stagesA | List per-stage checkpoint logs for an assessment run. Requires assessments:read. |
| air_get_assessment_input_artifactsA | List artifacts used as inputs when the assessment report was generated. Requires assessments:read. |
| air_create_assessment_draftA | Create an assessment draft without starting the pipeline. Requires assessments:write. |
| air_start_assessmentA | Start a risk assessment on a project. Consumes org credits and dispatches the risk pipeline. Requires assessments:write. Returns assessmentPid. |
| air_retry_assessmentA | Retry a failed assessment from the last completed stage. Requires assessments:write and consumes credits. |
| air_get_domain_portfolioA | Domain-level portfolio dashboard. Requires portfolio:read (fullPipeline preset). Domain-scoped API keys only work for their bound domain. |
| air_wait_for_document_extractionA | Poll air_list_documents until sourcePid reaches connected or error, or timeout. Returns an MCP Task handle immediately; poll tasks/get until completed. Uses exponential backoff per async-jobs guidance. |
| air_wait_for_assessmentA | Poll air_get_assessment until completed, failed, or reportAvailable, or timeout. Returns an MCP Task handle immediately; poll tasks/get until completed. Uses exponential backoff per async-jobs guidance. |
| air_run_assessment_from_fileA | Upload a local file, wait for extraction, start assessment on the new artifact. Consumes credits. Requires projects:write and assessments:write. Returns an MCP Task handle immediately. Reads filePath with your OS user permissions. |
| air_run_full_assessment_pipelineA | Start assessment on existing artifacts, wait for completion, return report summary. Consumes credits. Returns an MCP Task handle immediately; poll tasks/get until completed. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| run-assessment-workflow | Guide through discover → upload → extract → assess → report using AIR MCP tools |
| review-assessment-report | Fetch and summarize an assessment report by assessmentPid |
| explore-portfolio | Explore domain portfolio dashboard for governance gaps (API key access) |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/VericyIO/mcp-air'
If you have feedback or need assistance with the MCP directory API, please join our Discord server