Skip to main content
Glama

agentguard

by io.tooloracle
OverviewDiscussionsAdmin

Server Details

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

Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.

If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.

Status
Unhealthy
Last Tested
Transport
Streamable HTTP
URL
Repository
ToolOracle/agentguard
GitHub Stars
0

TDQS

A3.6/5.0

Scored across 24 tools

Disambiguation3/5

Most tools have distinct purposes, but there is notable overlap: output_safety_scan and secret_exposure_check both detect secrets/PII, and payment_policy_check vs spend_limit_check relate to payment limits. The descriptions help, but an agent may struggle to choose among the many similar 'check' tools.

Naming Consistency4/5

Tool names are overwhelmingly snake_case with a noun-based prefix followed by a verb or 'check' (e.g., rate_limit_check, audit_log_query). Minor deviations like 'decision_explain' and 'emergency_kill' still fit the readable pattern, so naming is mostly consistent.

Tool Count3/5

24 tools is on the heavy side but within the borderline range. The domain of agent security and governance justifies many specialized checks, though some tools could potentially be consolidated (e.g., output_safety_scan and secret_exposure_check).

Completeness4/5

The tool surface covers the full guardrail lifecycle: pre-execution checks, approval workflows, emergency controls, post-execution auditing, and metrics. Gaps include no policy management (create/update) and no tenant administration, but these are not critical for the server's apparent purpose.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 24 tool updates
    • First observedapproval_list
    • First observedapproval_required
    • First observedapproval_resolve
    • First observedaudit_log_query
    • First observedaudit_log_write
    • First observedcross_tool_anomaly_check
    • First observeddecision_explain
    • First observedemergency_kill
    • First observedguard_metrics
    • First observedoutput_safety_scan
    • First observedpayload_safety_check
    • First observedpayment_policy_check
    • First observedpolicy_preflight
    • First observedpolicy_register
    • First observedrate_limit_check
    • First observedreplay_guard_check
    • First observedscope_check
    • First observedsecret_exposure_check
    • First observedsession_validate
    • First observedspend_limit_check
    • First observedtenant_policy_check
    • First observedthreat_intel_check
    • First observedtool_manifest_verify
    • First observedtool_risk_score

Related MCP Connectors

Related MCP Servers

  • aegis

    Acacian
    A
    license
    A
    quality
    A
    maintenance
    Policy-based governance for AI agent tool calls. YAML policies, approval gates, risk assessment, and audit logging across LangChain, OpenAI, Anthropic, and MCP.
    5
    58 PyPI
    15
    MIT

  • guardrails-mcp-server

    ExpertVagabond
    A
    license
    Not graded
    quality
    B
    maintenance
    MCP server for AI agent security guardrails. Provides input validation, prompt injection detection, PII redaction, output filtering, policy enforcement, rate limiting, and comprehensive audit logging.
    42 npm
    1
    MIT
  • SentinelGate by Sentinel-Gate

    SentinelGateofficial

    Sentinel-Gate
    A
    license
    Not graded
    quality
    A
    maintenance
    Open-source MCP proxy that enforces security policies, content scanning, and audit logging between AI agents and tool servers
    25
    AGPL 3.0
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources