--- title: "Get the calling agent's own profile" method: GET path: "/v1/agents/me" tags: ["Agents"] --- # Get the calling agent's own profile `GET /v1/agents/me` ## Request - Base URL: `https://api.1claw.co` - URL: `https://api.1claw.co/v1/agents/me` - Auth: HTTP bearer ## Response `200` Agent self profile - AgentSelfResponse - `id` string, uuid - `name` string - `description` string - `org_id` string, uuid - `scopes` string[] - `is_active` boolean - `intents_api_enabled` boolean - `created_by` string, uuid - `created_at` string, date-time - `expires_at` string, date-time - `last_active_at` string, date-time - `ssh_public_key` string: Ed25519 SSH public key (base64-encoded) - `ecdh_public_key` string: P-256 ECDH public key (base64 SEC1 uncompressed point) - `shroud_enabled` boolean: Whether this agent routes LLM traffic through the Shroud TEE proxy - `shroud_config` ShroudConfig: Per-agent Shroud LLM Proxy configuration - `pii_policy` 'block' | 'redact' | 'warn' | 'allow': How PII detections are handled - `injection_threshold` number: Prompt injection score threshold (0.0–1.0). Requests above are blocked - `context_injection_threshold` number: Context injection score threshold (0.0–1.0) - `allowed_providers` string[]: LLM providers this agent may use (empty = all) - `allowed_models` string[]: Specific models allowed (empty = all) - `denied_models` string[]: Models explicitly blocked - `max_tokens_per_request` integer: Maximum input tokens per request - `max_requests_per_minute` integer: Rate limit (requests per minute) - `max_requests_per_day` integer: Rate limit (requests per day) - `daily_budget_usd` number: Daily LLM spend cap in USD (0 = unlimited) - `enable_secret_redaction` boolean: Whether vault secrets are redacted from prompts/responses - `enable_response_filtering` boolean: Whether response credential scanning is active - `unicode_normalization` UnicodeNormalizationConfig: Unicode normalization and homoglyph detection settings - `enabled` boolean: Enable Unicode normalization - `strip_zero_width` boolean: Remove zero-width and invisible Unicode characters - `normalize_homoglyphs` boolean: Replace look-alike characters (e.g., Cyrillic а → Latin a) - `normalization_form` 'NFC' | 'NFKC' | 'NFD' | 'NFKD': Unicode normalization form to apply - `command_injection_detection` CommandInjectionConfig: Shell/command injection detection settings - `enabled` boolean: Enable command injection detection - `action` 'block' | 'sanitize' | 'warn' | 'log': Action when command injection is detected - `patterns` 'default' | 'strict' | 'custom': Pattern strictness level - `custom_patterns` string[]: Custom regex patterns for detection (only used when patterns=custom) - `social_engineering_detection` SocialEngineeringConfig: Social engineering and manipulation detection settings - `enabled` boolean: Enable social engineering detection - `action` 'block' | 'warn' | 'log': Action when manipulation attempts are detected - `sensitivity` 'low' | 'medium' | 'high': Detection sensitivity level - `encoding_detection` EncodingDetectionConfig: Encoding/obfuscation detection settings - `enabled` boolean: Enable encoding detection - `action` 'block' | 'decode' | 'warn' | 'log': Action when obfuscated content is detected - `detect_base64` boolean: Detect Base64-encoded content - `detect_hex` boolean: Detect hex-encoded content (\\x41, 0x41) - `detect_unicode_escape` boolean: Detect Unicode escape sequences (\\u0041) - `network_detection` NetworkDetectionConfig: Suspicious URL/domain detection settings - `enabled` boolean: Enable network/URL detection - `action` 'block' | 'warn' | 'log': Action when suspicious URLs are detected - `blocked_domains` string[]: Domains to always block (e.g., pastebin.com, ngrok.io) - `allowed_domains` string[]: Domains to always allow (allowlist mode when non-empty) - `filesystem_detection` FilesystemDetectionConfig: Filesystem path detection settings - `enabled` boolean: Enable filesystem path detection (disabled by default as it can be noisy) - `action` 'block' | 'sanitize' | 'warn' | 'log': Action when filesystem paths are detected - `blocked_paths` string[]: Path patterns to block (e.g., /etc/passwd, ~/.ssh) - `sanitization_mode` 'block' | 'surgical' | 'log_only': Global behavior when threats are detected (block=reject, surgical=remove only malicious parts, log_only=audit without action) - `threat_logging` boolean: Whether to log all detected threats to audit (even when action is allow/warn) - `tool_call_inspection` ToolCallPolicy: Tool/function call inspection settings - `enabled` boolean: Enable tool call inspection - `allowed_tool_names` string[]: Allowed tool/function names (empty = all allowed) - `denied_tool_names` string[]: Denied tool/function names - `scan_arguments` boolean: Scan tool call arguments for credential exfiltration - `block_credential_exfil` boolean: Block tool calls that appear to exfiltrate credentials - `action` 'block' | 'sanitize' | 'warn' | 'log': Action when a tool call violation is detected - `output_policy` OutputPolicy: Output content policy settings for LLM responses - `enabled` boolean: Enable output content policies - `blocked_patterns` string[]: Custom regex patterns to block in responses - `blocked_entities` string[]: Named entities to block (e.g., competitor names) - `block_harmful_content` boolean: Block responses containing harmful content categories - `harmful_categories` string[]: Harm categories to block - `action` 'block' | 'sanitize' | 'warn' | 'log': Action when output policy is violated - `secret_injection_detection` SecretInjectionConfig: Detects credentials injected into prompts that are not from the vault - `enabled` boolean: Enable secret injection detection - `action` 'block' | 'sanitize' | 'warn' | 'log': Action when injected credentials are detected - `sensitivity` 'low' | 'medium' | 'high': Detection sensitivity level - `advanced_redaction` AdvancedRedactionConfig: Advanced secret redaction settings (base64-encoded, split, prefix leaks) - `enabled` boolean: Enable advanced redaction checks - `detect_base64_encoded` boolean: Detect base64-encoded vault secrets - `detect_split_secrets` boolean: Detect secrets split across tokens or messages - `detect_prefix_leak` boolean: Detect partial/prefix leaks of vault secrets - `min_secret_length` integer: Minimum secret length to consider for advanced matching - `semantic_policy` SemanticPolicy: Semantic/intent-level policy enforcement - `enabled` boolean: Enable semantic policy enforcement - `allowed_topics` string[]: Topics the agent is allowed to discuss (empty = all) - `denied_topics` string[]: Topics to block - `allowed_tasks` string[]: Tasks the agent is allowed to perform (empty = all) - `denied_tasks` string[]: Tasks to block (e.g., code_generation, data_export) - `action` 'block' | 'sanitize' | 'warn' | 'log': Action when semantic policy is violated - `flagged_request_retention_days` integer: Number of days to retain flagged request bodies for replay/investigation - `streaming_inspection_mode` 'rolling' | 'holdback': How streamed LLM responses are inspected before release. `rolling` (default) releases text behind a tail buffer at least as long as the org's longest vault secret (capped at 256 bytes; longer secrets are matched by prefix); `holdback` buffers `streaming_holdback_chars` for full parity with buffered inspection. Tool-call deltas are always held until the call is complete. - `streaming_holdback_chars` integer: Characters held back per stream in holdback mode (default 512) - `max_concurrent_streams` integer: Open streaming responses allowed per agent key (default 20; 429 with Retry-After beyond it) ## Other responses - `403`: Insufficient permissions --- [API](https://skmtc.dev/1claw/apis/1claw-api.md) · [All operations](https://skmtc.dev/1claw/apis/1claw-api/llms.txt) · [OpenAPI document](https://skmtc.dev/1claw/apis/1claw-api/revisions/ae109b496830?raw)