> ## Documentation Index > Fetch the complete documentation index at: https://docs.labelbox.com/llms.txt > Use this file to discover all available pages before exploring further. # Test an MCP server connection and list its tools > Opens a live connection to an MCP server using exactly the credential resolution a session would use, and returns the tools it advertises. A server that cannot be reached or authenticated is still HTTP 200 with ok=false, so inspect that field rather than relying on the status code. Pass vault_ids to probe authenticated; omit them to probe anonymously. ## OpenAPI ````yaml /managed-agents/openapi.yaml post /managed-agents/v1/mcp/probe openapi: 3.1.0 info: title: Managed Agents API version: 0.13.0 description: >- The Recursion Managed Agents REST API. Authenticate with a Recursion API key as a bearer token. An organization-scoped key acts in its own organization and needs nothing else; a tenant-scoped key must also send `x-organization-id` with an organization id or `default`. Field names follow each operation's published schema. servers: - url: https://api.recursion.labelbox.com security: - bearerAuth: [] paths: /managed-agents/v1/mcp/probe: post: tags: - Vaults summary: Test an MCP server connection and list its tools description: >- Opens a live connection to an MCP server using exactly the credential resolution a session would use, and returns the tools it advertises. A server that cannot be reached or authenticated is still HTTP 200 with ok=false, so inspect that field rather than relying on the status code. Pass vault_ids to probe authenticated; omit them to probe anonymously. operationId: managedAgentsProbeMCPServer requestBody: content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsProbeMCPServerRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsMCPProbeResponse' description: >- Response body of POST /v1/mcp/probe: the result of one live connection attempt to an MCP server, run through the same URL and vault resolution a real session uses. This envelope is a verdict rather than a resource: a server that is down is still HTTP 200 with ok=false, so a caller can distinguish "the server you configured is unreachable" from "this API is unreachable". Nothing is persisted by a probe. '400': description: The request was rejected by schema or semantic validation. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '401': description: The caller is unauthenticated. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '403': description: The caller lacks a required permission or capability. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorForbidden' '404': description: No such resource is reachable for this caller. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorNotFound' '409': description: >- The request conflicts with the resource state, or with an in-flight idempotent replay. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '413': description: The request exceeds a size or transaction budget. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '415': description: The request body uses a media type this operation does not accept. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorUnsupportedMediaType' '429': headers: Retry-After: description: Seconds the caller should wait before retrying. schema: type: string style: simple description: A rate limit is exhausted. Honor `Retry-After`. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '500': description: An unexpected server-side failure. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '502': description: The service returned an invalid response. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorBadGateway' '503': headers: Retry-After: description: Seconds the caller should wait before retrying. schema: type: string style: simple description: A dependency is unavailable. Retryable. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiError' '504': headers: Retry-After: description: When to retry, as delay seconds or an HTTP date. schema: type: string description: The service did not respond before the timeout. Retryable. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorGatewayTimeout' components: schemas: ManagedAgentsProbeMCPServerRequest: description: >- Request body for a live connection test against an MCP server, running the same credential resolution a session would. An unreachable server is reported in the response body, not as an HTTP error. properties: server_url: description: >- The MCP server to connect to. Must be http or https and must not embed credentials. type: string vault_ids: description: >- Vaults whose credentials may be used, scoped exactly as a session's grant is. Omit to probe unauthenticated. items: type: string type: array required: - server_url type: object example: server_url: https://example.com vault_ids: - example ManagedAgentsMCPProbeResponse: description: >- Response body of POST /v1/mcp/probe: the result of one live connection attempt to an MCP server, run through the same URL and vault resolution a real session uses. This envelope is a verdict rather than a resource: a server that is down is still HTTP 200 with ok=false, so a caller can distinguish "the server you configured is unreachable" from "this API is unreachable". Nothing is persisted by a probe. properties: credential_matched: description: >- True when a credential from the named vaults was opened and attached to the request. It reports whether this attempt was authenticated, not whether a credential exists: a credential that matched the server URL but could not be opened reports false and sets credential_unopenable, because nothing was sent. type: boolean credential_unopenable: description: >- Set when a credential matched this server URL and could not be opened, so the request carried no auth header. external_reference means the material is held outside this service and must be re-entered here; material_missing means the credential row carries no stored value. Empty when none matched or the match was usable. enum: - external_reference - material_missing type: string deployment_authorized: description: >- True when a deployment-owned access-token policy authorizes this endpoint for the organization and each request mints a token for the deployment's reader identity. Distinct from credential_matched: no vault credential is involved. For endpoints that answer discovery unauthenticated (Google hosted MCPs), a green tool list proves connectivity and discovery, not provider-side IAM — only a real tool call does. type: boolean error: description: >- Operator-facing diagnostic when the probe failed. Never contains credential material. type: string ok: description: >- True when the server completed the handshake and returned a tool list. type: boolean protocol_version: description: The MCP protocol version used. type: string reachable: description: >- True when the handshake succeeded, even if listing tools then failed. type: boolean server_name: description: >- What the server called itself during the handshake, which is how an operator confirms the URL reached the intended service. type: string tools: description: >- Tools the server advertised on this attempt. Always an array and never null: empty means the handshake succeeded but the server offered no tools, or listing them failed, which is what ok=false plus reachable=true reports. items: $ref: '#/components/schemas/ManagedAgentsMCPProbeTool' type: array required: - ok - reachable - credential_matched - deployment_authorized - tools type: object example: credential_matched: true credential_unopenable: external_reference deployment_authorized: true error: example ok: true protocol_version: example reachable: true server_name: example tools: - description: example name: example-name ManagedAgentsApiError: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - analytics - analytics_not_ready - artifact_fetch_unavailable - artifact_generation_mismatch - artifact_hash_mismatch - artifact_invalid_events - artifact_invalid_json - artifact_not_allowlisted - artifact_size_mismatch - atlassian_rate_limited - atlassian_unavailable - atomic_ingest_timeout - auth_unavailable - automation_event_source_invalid - automation_memory_unavailable - automation_reference_invalid - automation_runs_unconfigured - automations_unconfigured - bad_gateway - built_in_catalog_unavailable - built_in_integrations_disabled - built_in_integrations_unconfigured - compute_offerings_unavailable - conflict - content_store_request_canceled - content_store_unavailable - content_store_upload_timeout - credential_encryption_unconfigured - delegate_preparation_failed - entity_family_not_permitted - environment_not_verified - evaluation_cancellation_pending - evaluation_deletion_pending - event_admission_unavailable - event_ingress_unavailable - event_source_verification_credential_invalid - event_sources_unconfigured - execution_unconfigured - file_quota_exceeded - file_storage_unconfigured - forbidden - gateway_timeout - gestalt_unconfigured - github_rate_limited - github_unavailable - handoff_access_invalid - handoff_access_unavailable - handoff_access_unsupported - handoff_capture_unavailable - handoff_requires_retest - handoff_revoke_unavailable - handoff_signal_unavailable - idempotency_conflict - idempotency_in_progress - idempotency_unavailable - ingest_policy_changed - ingest_policy_not_found - ingest_policy_revoked - integrations_unconfigured - internal_error - invalid_json - invalid_pull_request_review_result - invalid_request - invalid_scope - invariant_violation - launchdarkly_rate_limited - launchdarkly_unavailable - live_fleet_unconfigured - managed_agents_unavailable - merge_key_rejected - merge_link_unavailable - merge_rate_limited - merge_unavailable - missing_dependency - model_gateway_metadata_missing - model_gateway_unconfigured - model_gateway_unreachable - mutation_transaction_budget_exceeded - not_found - page_token_expired - payload_too_large - persistence_busy - precondition_failed - precondition_required - provider_registration_unsupported - provider_selection_unsupported - rate_limit_exceeded - rate_limited - repository_automation_unconfigured - request_too_large - reserved_source_type - revision_conflict - run_log_store_unavailable - runner_image_resolution_failed - sandbox_provider_disabled - service_unavailable - session_analyst_busy - session_analyst_model_unavailable - session_analyst_unconfigured - session_start_admission_unavailable - session_start_not_admitted - setup_fallback_environment_unsafe - setup_run_finished - setup_run_in_progress - setup_run_limit - setup_run_not_started - setup_runs_unavailable - skill_storage_unconfigured - slack_channels_rejected - slack_channels_unavailable - slack_channels_unconfigured - slack_connection_malformed - slack_event_intake_unavailable - slack_installation_mismatch - slack_missing_scope - slack_rate_limited - slack_reapproval_required - source_ownership_mismatch - source_revision_conflict - spanner_unavailable - streaming_unsupported - submission_transaction_budget_exceeded - task_version_number_conflict - team_board_unconfigured - too_many_streams - unauthorized - unsupported_media_type - vault_creation_retired - version_content_conflict - webhook_delivery_too_large - workspace_boundary_denied message: type: string minLength: 1 description: Human-readable error message. details: description: Optional structured error details. type: object propertyNames: type: string additionalProperties: {} required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorForbidden: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - forbidden message: type: string minLength: 1 description: Human-readable error message. details: description: Optional structured error details. type: object propertyNames: type: string additionalProperties: {} required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorNotFound: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - not_found message: type: string minLength: 1 description: Human-readable error message. details: description: Optional structured error details. type: object propertyNames: type: string additionalProperties: {} required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorUnsupportedMediaType: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - unsupported_media_type message: type: string minLength: 1 description: Human-readable error message. details: description: Optional structured error details. type: object propertyNames: type: string additionalProperties: {} required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorBadGateway: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - bad_gateway message: type: string minLength: 1 description: Human-readable error message. details: description: Optional structured error details. type: object propertyNames: type: string additionalProperties: {} required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorGatewayTimeout: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - gateway_timeout message: type: string minLength: 1 description: Human-readable error message. details: description: Optional structured error details. type: object propertyNames: type: string additionalProperties: {} required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsMCPProbeTool: description: >- One tool advertised by a probed MCP server, reported verbatim from its tools/list response. Appears only inside MCPProbeResponse.tools; the service does not persist or validate these entries, so their presence proves the server answered, not that the tool works. properties: description: description: >- The tool's own self-description as returned by the server, passed through verbatim. Absent when the server advertised the tool without one. type: string name: description: >- The tool name as the MCP server reported it, which is the name an agent would call it by. type: string required: - name type: object example: description: example name: example-name securitySchemes: bearerAuth: type: http scheme: bearer description: A Recursion API key, created in the console under API keys. ````