Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.tooloracle/agentguard

REMOTE · FEEDORACLE.IO

AgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits.

Available components

0 this week 25 Trust /100

Last scanned (16 hours ago)

Scores higher than 10% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Security

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability0
Schema Quality & AI Usability0
  • Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.Unverified
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
  • Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Tool Safety0
  • Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Capabilities0
  • Capabilities not yet verified: we couldn't read the endpoint's capabilities.Unverified

Unverified: 5 categories

Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

What we tested

Checks we ran (5)

  • TLS certificate
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport

Checks we could not complete (6)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation not yet verified: we couldn't confirm whether this endpoint requires it.
  • Schema quality in Schema Quality & AI Usability (scores 0 for this)Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.
  • Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).
  • Tool coverage in Tool Coverage (scores 0 for this)Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
  • Tool safety in Tool Safety (scores 0 for this)Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
  • Capabilities in Capabilities (scores 0 for this)Capabilities not yet verified: we couldn't read the endpoint's capabilities.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 28 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 26 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 11 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 5 Aug 26 0
    • Endpoint reachability: reachable → not serving MCP ▼ security
    • Stability: 0.30 → unverified ▼ security
    • Transport: pass → fail ▼ security
    • HSTS header: fail → pass ▲ security
    • Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the whole tool list to see what that exposes. security
    • Capabilities: fail → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • First check of Schema quality: unverified functional
  • 31 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://feedoracle.io/guard-oracle/mcp/

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=feedoracle.io CN=YE1,O=Let's Encrypt,C=US 16 Nov 2026 14 Feb 2027 ECDSA 256 ECDSA-SHA384 644b57d80753e639dfbb47784790bfe03a0
SANs: feedoracle.io, www.feedoracle.io
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of feedoracle.io. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
io. DS published 38690 8 Verified
feedoracle.io. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Inconclusive

We could not reach the endpoint well enough to judge its authorisation posture.

Result Inconclusive
HTTP status 404
Header Value
strict-transport-security max-age=31536000; includeSubDomains; preload
content-security-policy default-src 'self'; script-src 'self' 'unsafe-inline'; style-src 'self' 'unsafe-inline' https://fonts.googleapis.com; img-src 'self' data:; font-src 'self' https://fonts.gstatic.com; connect-src 'self' https://api.feedoracle.io https://analytics.feedoracle.io https://fonts.googleapis.com; object-src 'none'; base-uri 'self'; form-action 'self' https://checkout.stripe.com;
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy geolocation=(), microphone=(), camera=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://feedoracle.io/guard-oracle/mcp/ HTTP error 404
http (plaintext) http://feedoracle.io/guard-oracle/mcp/ HTTPS enforced 308 https://feedoracle.io/guard-oracle/mcp/
MCP tools · 24 exposed · ~2,510 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
approval_list ~92

List approval requests. Filter by status (pending/approved/denied/all), agent_id, or tool_name. Shows summary stats.

NameTypeReqDescription
agent_idstring–Filter by agent ID
limitinteger–Max results (default: 50, max: 200)
statusstring–Filter by status (default: pending)
tool_namestring–Filter by tool name

No output schema declared.

No examples provided.

approval_required ~93

Check if a tool call requires human approval before execution. Returns requires_approval=true/false with matched policy list. Set register_pending=true to create a trackable approval request with an approval_url for human review.

NameTypeReqDescription
agent_idstring–Agent identifier
register_pendingboolean–Create pending approval record
tool_argsobject–Tool arguments
tool_namestringyesTool to check

No output schema declared.

No examples provided.

approval_resolve ~96

Resolve a pending approval request. Approve or deny a tool call that was flagged for human review. Updates agent state and creates audit trail. Requires authentication.

NameTypeReqDescription
approved_bystring–Identity of the approver (name/email/agent_id)
decisionstringyesApprove or deny
reasonstring–Optional reason for the decision
request_idstringyesThe approval request ID to resolve

No output schema declared.

No examples provided.

audit_log_query ~154

Query the persistent audit trail. Filter by agent, tool, decision, time range. Returns signed entries with tamper-detection. Use for compliance reporting, anomaly detection, or agent behaviour analysis.

NameTypeReqDescription
agent_idstring–Filter by agent ID
decisionstring–Filter: allowed|denied|flagged|approved
limitinteger–Max entries (default 50, max 500)
offsetinteger–Pagination offset
sincestring–ISO timestamp start (e.g. 2026-03-27T00:00:00Z)
tool_namestring–Filter by tool name
untilstring–ISO timestamp end

No output schema declared.

No examples provided.

audit_log_write ~167

Write a tool call result to the persistent, signed audit log. Call this AFTER tool execution with the outcome. Each entry is cryptographically signed for tamper-evidence. Essential for compliance, DORA, MiCA audit trail requirements.

NameTypeReqDescription
agent_idstring–Agent that made the call
decisionstring–allowed|denied|flagged|approved
duration_msinteger–Execution time in milliseconds
outcomestring–success|error|timeout
reasonstring–Why this decision was made
risk_scoreinteger–Risk score at time of call
session_idstring–Session identifier
tool_argsobject–Arguments used
tool_namestringyesTool that was executed

No output schema declared.

No examples provided.

cross_tool_anomaly_check ~93

Detect anomalous tool usage patterns across an agent recent history. Checks risky tool combinations (AML-then-payment, wallet-recon-then-transfer), high call frequency, repeated denials, broad reconnaissance, elevated risk scores.

NameTypeReqDescription
agent_idstringyesAgent to analyze
sensitivitystring–low|medium|high
window_secondsinteger–Lookback seconds (default 300)

No output schema declared.

No examples provided.

decision_explain ~113

Get a human-readable explanation of why a tool call was allowed or denied. Pass request_id from a previous policy_preflight for stored explanation, or provide tool_name + tool_args for fresh analysis. Explains matched policies, risk score breakdown, and recommendation.

NameTypeReqDescription
agent_idstring–Agent identifier
request_idstring–request_id from previous preflight (optional)
tool_argsobject–Arguments to analyze
tool_namestring–Tool to analyze (if no request_id)

No output schema declared.

No examples provided.

emergency_kill ~107

Emergency kill-switch. Immediately terminates agent session(s), revokes pending approvals, blocks rate limits, and audit-logs the emergency. Use for: compromised agents, runaway automation, suspicious behavior. kill_type: full|session_only|soft.

NameTypeReqDescription
agent_idstring–Agent to kill
kill_typestring–full|session_only|soft
reasonstring–Why emergency kill was triggered
session_idstring–Specific session to kill

No output schema declared.

No examples provided.

guard_metrics ~50

AgentGuard operational metrics. Returns decision stats, top agents/tools, risk distribution, daily activity, approval stats, and tier distribution.

NameTypeReqDescription
daysinteger–Time window in days (default: 30)

No output schema declared.

No examples provided.

output_safety_scan ~120

Post-execution output scanner. Checks tool output for PII leaks (email, phone, SSN, IBAN), secret exposure, data exfiltration patterns (outbound URLs, base64), and tool poisoning (injected instructions). Verdict: clean|warn|flag|block.

NameTypeReqDescription
agent_idstring––
outputstringyesTool output text or JSON to scan
strictboolean–Block on any high-severity finding
tool_namestring–Name of the tool that produced this output

No output schema declared.

No examples provided.

payload_safety_check ~122

Comprehensive safety scan for injection attacks and dangerous patterns. Detects: prompt injection, jailbreak/DAN attempts, role hijacking, SQL injection (UNION/DROP/OR 1=1), XSS, Python/JS/Shell code injection, path traversal, oversized payloads, null bytes. Returns safe=true/false with finding list and block/allow decision.

NameTypeReqDescription
agent_idstring–Agent identifier
payload–yesPayload to scan (string or object)
strict_modeboolean–Block on any finding (default: false)

No output schema declared.

No examples provided.

payment_policy_check ~141

Validate a payment against policy rules before execution. Checks amount limits (>100k warns, >1M blocks), recipient allowlist/denylist, supported currencies/networks, AML reporting thresholds, and MiCA flags. Returns approved/rejected with full violation list and risk score.

NameTypeReqDescription
agent_idstring–Agent identifier
amountnumberyesPayment amount
currencystring–Currency code (USD, EUR, USDC, ETH...)
networkstring–Payment network (ethereum, base, sepa...)
purposestring–Payment purpose (required for compliance)
recipientstring–Recipient address or ID

No output schema declared.

No examples provided.

policy_preflight ~110

Pre-flight security check before any tool call. Evaluates all policies, computes risk score, checks rate limits, and returns allow/deny/require_approval decision. Call this BEFORE executing any agent tool. Writes to audit log automatically.

NameTypeReqDescription
agent_idstring–Unique identifier for the calling agent
session_idstring–Session identifier (optional)
tool_argsobject–Arguments for the tool call
tool_namestringyesName of tool about to be called

No output schema declared.

No examples provided.

policy_register ~90

View the central policy registry. Query tiers (T1-T4), tool classifications, escalation rules. Actions: summary (default), lookup (by tool_name), tiers, rules, tools (by tier_id).

NameTypeReqDescription
actionstring–What to query (default: summary)
tier_idstring–Tier ID for tools action
tool_namestring–Tool name for lookup action

No output schema declared.

No examples provided.

rate_limit_check ~73

Check if an agent has exceeded rate limits. Returns per-window usage (minute/hour/day) with percentage used. Limits: 200/min, 5000/hr, 50000/day per agent. Use before high-frequency tool calls or for agent health monitoring.

NameTypeReqDescription
agent_idstringyesAgent ID to check

No output schema declared.

No examples provided.

replay_guard_check ~112

Detect replay attacks — identical requests sent multiple times in a time window. Uses SHA256 fingerprint of (agent_id + tool_name + args). Default window: 300 seconds (5 min). Returns is_replay=true/false with duplicate count and first/last seen timestamps.

NameTypeReqDescription
agent_idstring–Agent identifier
tool_argsobject–Tool arguments (used for fingerprint)
tool_namestringyesTool name to check
window_secondsinteger–Replay window in seconds

No output schema declared.

No examples provided.

scope_check ~82

Check if agent has required scope for a tool. Roles: admin, compliance_officer, trader, auditor, developer, readonly. Returns has_scope + missing scope + granting roles.

NameTypeReqDescription
agent_idstring––
rolestring––
scopesarray––
session_idstring––
tool_namestringyes–

No output schema declared.

No examples provided.

secret_exposure_check ~108

Deep scan any text/payload for secrets, credentials, and PII. Detects: API keys (OpenAI, GitHub, AWS), tokens (Slack, Bearer), private keys (ETH, Bitcoin), credentials (passwords, secrets), and PII (emails, credit cards, SSNs). Returns findings with severity and remediation guidance.

NameTypeReqDescription
payloadstringyesText or JSON string to scan
scan_typestring–all | keys | tokens | pii

No output schema declared.

No examples provided.

session_validate ~96

Create/validate/invalidate agent sessions with role, scopes, TTL and call budget. Actions: create|validate|invalidate|info.

NameTypeReqDescription
actionstringyes–
agent_idstring––
call_budgetinteger––
rolestring––
scopesarray––
session_idstring––
tenant_idstring––
ttl_secondsinteger––

No output schema declared.

No examples provided.

spend_limit_check ~117

Check if a payment amount stays within agent spend limits. Default limits: 10,000/call, 50,000/hr, 200,000/day. Trusted agents: 100,000/call, 500,000/hr, 2,000,000/day. Returns within_limits=true/false with headroom percentage.

NameTypeReqDescription
agent_idstring–Agent identifier
amountnumberyesAmount to check
currencystring–Currency code
trust_levelstring–default or trusted

No output schema declared.

No examples provided.

tenant_policy_check ~83

Multi-tenant governance. Tenants: default, fintech_eu (MiCA/DORA), defi_protocol, enterprise_read. Checks tool blocklists, max risk scores, spend limits. Actions: check|list.

NameTypeReqDescription
actionstring––
agent_idstring––
tenant_idstring––
tool_namestring––

No output schema declared.

No examples provided.

threat_intel_check ~91

Check entity against threat intelligence. Auto-detects ETH addresses, IPs, domains. Checks sanctions (Tornado Cash), disposable services, behavioral analysis from audit log. Returns threat_level: none|low|medium|high|critical.

NameTypeReqDescription
agent_idstring––
entitystringyesAddress, IP, domain or agent_id to check
entity_typestring––

No output schema declared.

No examples provided.

tool_manifest_verify ~96

Supply-chain verification for MCP tools. Checks publisher identity against allowlist, scans tool descriptions for prompt injection, validates server domain and signing capability. Verdict: trusted|caution|block.

NameTypeReqDescription
publisherstring–Claimed publisher name
server_urlstring–MCP server URL to verify
tool_descriptionstring–Tool description to scan for injections
tool_namestring–Tool name to check

No output schema declared.

No examples provided.

tool_risk_score ~104

Compute 0-100 risk score for any tool + input combination. 0=minimal risk (read-only), 100=critical (payment/irreversible). Detects secrets, injection attempts, high-value amounts. Use before deciding whether to proceed with a tool call.

NameTypeReqDescription
agent_idstring–Agent identifier (affects trust factor)
tool_argsobject–Tool arguments to analyze
tool_namestringyesTool name to score

No output schema declared.

No examples provided.

Install

How do I install the io.tooloracle/agentguard MCP server?

io.tooloracle/agentguard is a hosted endpoint at https://feedoracle.io/guard-oracle/mcp/, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · feedoracle.io

# add to Claude Code
claude mcp add --transport http io-tooloracle-agentguard 'https://feedoracle.io/guard-oracle/mcp/'
Common questions

What is the io.tooloracle/agentguard MCP server?

io.tooloracle/agentguard is an MCP server listed in the public MCP registry as io.tooloracle/agentguard. AgentGuard, 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits. This page covers its hosted endpoint (https://feedoracle.io/guard-oracle/mcp/).

Is the io.tooloracle/agentguard MCP server safe to use?

io.tooloracle/agentguard scores 25 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.tooloracle/agentguard MCP server expose?

io.tooloracle/agentguard exposes 24 tools: policy_preflight, tool_risk_score, approval_required, audit_log_write, audit_log_query, and 19 more. Their descriptions and schemas cost roughly 2,510 tokens of context every time the server is loaded.

Does the io.tooloracle/agentguard MCP server require authentication?

Its publisher declares no required credentials for io.tooloracle/agentguard. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.

Is the io.tooloracle/agentguard MCP server still maintained?

io.tooloracle/agentguard is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the io.tooloracle/agentguard MCP server?

VerifyMCP ran 5 checks on io.tooloracle/agentguard, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 1 more. 6 items could not be completed, a gap on our side rather than a finding about io.tooloracle/agentguard: Authorization, Schema quality, Stability, Tool coverage and 2 more. 5 categories score 0 for that reason, because we only credit what we can confirm. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.