praesidiaVerify AI agents, check trust scores (0-100), fetch A2A agent cards, discover marketplace agents, apply guardrails for security and compliance. Use when user mentions agent verification, trust scores, agent discovery, A2A protocol, agent identity, agent marketplace, guardrails, security policies, content moderation, or asks "is this agent safe?" or "find agents that can [task]" or "apply guardrails to protect my agent".
Install via ClawdBot CLI:
clawdbot install msoica/praesidiaVerify AI agents, check trust scores (0-100), discover marketplace agents, and apply guardrails for security and compliance.
~/.openclaw/openclaw.json:{
"skills": {
"entries": {
"praesidia": {
"apiKey": "pk_live_your_key_here",
"env": {
"PRAESIDIA_API_URL": "https://api.praesidia.ai"
}
}
}
}
}For local development, use http://localhost:3000 as the URL.
User says: "Is agent chatbot-v2 safe?" / "Verify agent chatbot-v2"
Your action:
web_fetch({
url: "${PRAESIDIA_API_URL}/agents/chatbot-v2/agent-card",
headers: {
"Authorization": "Bearer ${PRAESIDIA_API_KEY}",
"Accept": "application/json"
}
})Present to user:
Example output:
✅ ChatBot V2 is verified and safe to use!
Trust Score: 92.5/100 (VERIFIED)
Status: ACTIVE
Capabilities: message:send, task:create, data:analyze
Compliance: SOC2, GDPR
Last verified: 2 days ago
Agent card: https://api.praesidia.ai/agents/chatbot-v2/agent-cardUser says: "What guardrails are configured for my agent?" / "Show me security policies for chatbot-v2"
Your action:
// First, get the user's organization ID from their profile or context
// Then fetch guardrails
web_fetch({
url: "${PRAESIDIA_API_URL}/organizations/${orgId}/guardrails?agentId=${agentId}",
headers: {
"Authorization": "Bearer ${PRAESIDIA_API_KEY}",
"Accept": "application/json"
}
})Present to user:
Example output:
Found 3 guardrails for ChatBot V2:
1. PII Detection (ENABLED)
- Type: ML | Category: SECURITY
- Scope: BOTH (input & output)
- Action: REDACT sensitive data
- Triggered: 45 times
2. Toxic Language Filter (ENABLED)
- Type: RULE | Category: CONTENT
- Scope: BOTH
- Action: BLOCK toxic content
- Triggered: 12 times
3. Financial Advice Warning (ENABLED)
- Type: LLM | Category: COMPLIANCE
- Scope: OUTPUT only
- Action: WARN if detected
- Triggered: 3 timesUser says: "What guardrail templates are available?" / "Show me security templates"
Your action:
web_fetch({
url: "${PRAESIDIA_API_URL}/organizations/${orgId}/guardrails/templates",
headers: {
"Authorization": "Bearer ${PRAESIDIA_API_KEY}",
"Accept": "application/json"
}
})Available Templates:
Content Moderation:
Security:
Compliance:
Brand Safety:
Accuracy:
User says: "Add PII detection to my chatbot" / "Apply toxic language filter to agent xyz"
Your action:
web_fetch({
url: "${PRAESIDIA_API_URL}/organizations/${orgId}/guardrails",
method: "POST",
headers: {
"Authorization": "Bearer ${PRAESIDIA_API_KEY}",
"Content-Type": "application/json"
},
body: JSON.stringify({
name: "PII Detection",
description: "Automatically detect and redact PII",
agentId: "${agentId}",
template: "PII_DETECTION",
type: "ML",
category: "SECURITY",
scope: "BOTH",
action: "REDACT",
severity: "HIGH",
isEnabled: true,
priority: 0
})
})Guardrail Options:
Type:
Category:
Scope:
Action:
Severity:
User says: "Check if this message passes guardrails: [content]"
Your action:
web_fetch({
url: "${PRAESIDIA_API_URL}/organizations/${orgId}/guardrails/validate",
method: "POST",
headers: {
"Authorization": "Bearer ${PRAESIDIA_API_KEY}",
"Content-Type": "application/json"
},
body: JSON.stringify({
content: "User's message here",
agentId: "${agentId}",
scope: "INPUT"
})
})Response shows:
User says: "Find public data analysis agents" / "Show me chatbot agents"
Your action:
web_fetch({
url: "${PRAESIDIA_API_URL}/agents/discovery?visibility=PUBLIC&search=data",
headers: { "Accept": "application/json" }
// Authorization optional for public agents (includes it for more results)
})Filters available:
?visibility=PUBLIC - public marketplace agents?role=SERVER - agents that provide services?role=CLIENT - agents that consume services?status=ACTIVE - only active agents?search=keyword - search by name/descriptionPresent to user:
Example output:
Found 2 public data analysis agents:
1. OpenData Analyzer (VERIFIED - 88.0/100)
- Capabilities: data:analyze, chart:generate, report:create
- Role: SERVER | Status: ACTIVE
- Card: https://api.praesidia.ai/agents/opendata-1/agent-card
2. CSV Processor (STANDARD - 70.0/100)
- Capabilities: file:parse, data:transform, export:json
- Role: SERVER | Status: ACTIVE
- Card: https://api.praesidia.ai/agents/csv-proc/agent-cardUser says: "Show my agents" / "List all my server agents"
Your action:
web_fetch({
url: "${PRAESIDIA_API_URL}/agents/discovery?role=SERVER",
headers: {
"Authorization": "Bearer ${PRAESIDIA_API_KEY}",
"Accept": "application/json"
}
})This returns all agents the user has access to (their own + team/org agents).
Present trust information clearly to help users make decisions:
| Trust Score | Level | Meaning | Recommendation |
|-------------|-------|---------|----------------|
| 90-100 | VERIFIED | Fully vetted, compliant, verified identity | ✅ Safe to use |
| 70-89 | STANDARD | Good reputation, basic verification | ✅ Generally safe |
| 50-69 | LIMITED | Minimal verification | ⚠️ Use with caution |
| 0-49 | UNTRUSTED | Not verified or poor reputation | ❌ Not recommended |
Always show the trust score numerically (e.g., 92.5/100) and the level (e.g., VERIFIED).
| Error | Meaning | What to tell user |
|-------|---------|-------------------|
| 401 Unauthorized | API key missing/invalid | "Check PRAESIDIA_API_KEY in ~/.openclaw/openclaw.json" |
| 403 Forbidden | No permission | "You don't have access to this agent" |
| 404 Not Found | Agent doesn't exist | "Agent not found. Check the agent ID" |
| 500 Server Error | Praesidia API issue | "Praesidia API temporarily unavailable. Try again" |
Fetch detailed agent card with trust data.
Auth: Required for private/team/org agents, optional for public
Returns: A2A agent card + Praesidia extensions (trust, compliance)
List/search agents with filters.
Auth: Optional (more results with auth)
Query params: role, status, visibility, search
Returns: Array of agent summaries with card URLs
When helping users with guardrails:
User: "Is agent xyz safe to use?"
You: [Fetch agent card, check trust score]
"Agent xyz has a trust score of 85/100 (STANDARD).
It's verified for basic operations. What would you like to use it for?"User: "I need an agent that can analyze spreadsheets"
You: [Search discovery with visibility=PUBLIC&search=spreadsheet]
"I found 3 spreadsheet analysis agents. The highest rated is..."User: "Show me all my agents that are inactive"
You: [Fetch discovery with status=INACTIVE]
"You have 2 inactive agents: [list with trust scores]"User: "I need to secure my chatbot against PII leaks"
You: [List available templates, recommend PII_DETECTION]
[Apply guardrail with REDACT action on BOTH scope]
"I've added PII Detection (ML-powered) to your chatbot.
It will automatically redact sensitive information in both
user inputs and bot responses."User: "My agent handles healthcare data. What guardrails should I add?"
You: [Check if HIPAA compliance is required]
[Recommend HIPAA_COMPLIANCE + PII_DETECTION + AUDIT_LOGGING]
"For healthcare data, I recommend these guardrails:
1. HIPAA Compliance (BLOCK on violations)
2. PII Detection (REDACT)
3. Medical Advice Warning (WARN)
Would you like me to apply these?"PRAESIDIA_API_KEY (required) - Your API key from https://app.praesidia.aiPRAESIDIA_API_URL (optional) - Defaults to https://api.praesidia.aihttps://api.praesidia.aihttp://localhost:3000AI Usage Analysis
Analysis is being generated… refresh in a few seconds.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection