MCP App StoreMCP App Store
from hope-agent734
Query Hope Agent's local SQLite log and session databases (read-only) to diagnose errors, trace tool failures, and verify fixes without asking users to paste lo
Provides read-only, tactical SQL query templates and guidance for inspecting Hope Agent's local SQLite databases (logs.db, sessions.db, async_jobs.db). It enables the agent to pull structured evidence — recent errors, slow tool calls, subagent failures, and token usage — and link logs back to conversations. The skill emphasizes safety: open DBs in readonly mode and never run mutating SQL.
Use when a user reports an error, slowdown, unexpected behavior, or asks "show me the logs". Also useful for ad-hoc analysis: token usage, recent failed subagent runs, or stuck async jobs. Start broad (recent ERROR logs) then drill into session/message rows.
Best used with agent runtimes that expose exec and a filesystem (desktop / server agents) such as Claude Code, local Codex/exec-enabled agents, or OpenClaw-style agents that can run shell commands.
A well-structured diagnostics skill for querying Hope Agent's local SQLite databases (logs, sessions, background jobs) in read-only mode. SKILL.md is comprehensive with clear schema docs, a rich query cookbook, and strong safety guardrails (SELECT-only enforcement, readonly flags, privacy caveats). No bundled scripts — all queries are run ad-hoc via exec. The iron rule on read-only access and explicit notes on when NOT to use this skill show thoughtful design.
Security: Enforces -readonly flag and ?mode=ro URI, explicitly bans write operations, warns about secrets in tool_result fields. Minor deduction for querying local DBs with potential sensitive data without explicit redaction in output. Code quality: Very thorough documentation, clear triggers, good query templates with LIMIT and time bounds. No actual scripts to evaluate, but the SKILL.md itself is well-written. Architecture: Good frontmatter, clear separation between query patterns and workflow guidance, solid 'when NOT to use' section. Could benefit from a references/ directory for schema details. Usefulness: Niche audience (Hope Agent users only) but solves a real common problem — self-service log diagnostics. The query cookbook alone is highly practical for that audience.
NGINX Integration
Integrate with NGINX via the Membrane CLI to query, manage, and proxy requests to NGINX for configuration, logs, and runtime operations.
Retriever (Membrane CLI)
Integrate Retriever search and discovery via the Membrane CLI — manage connections and run queries across Retriever data sources.
Starlark Dev
Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.
Canary — Post-Deploy Visual Monitor
Run a short post-deploy monitor that captures screenshots, checks console errors, and compares performance against baselines to detect regressions and page fail
CTF Write-up Generator
Generate a concise, reproducible submission-style CTF writeup with a one-path solution script, metadata, and a short checklist for fast verification.
Monitoring Stack Deployer
Deploy and configure production-ready monitoring stacks (Prometheus, Grafana, Datadog) with collectors, dashboards, and alerting rules for Kubernetes, Docker, o
Bash Pro
Defensive, production-grade Bash scripting patterns and CI/CD best practices: strict mode, safe argument parsing, testing with Bats, and tooling (ShellCheck/shf
Agent Browser — Core
Core usage guide for agent-browser: snapshot-and-ref browser automation to navigate pages, interact with elements, extract data, take screenshots, manage sessio