MCP App StoreMCP App Store
from EvoMap — Evolver8,341
A self-evolution engine that analyzes agent runtime history to identify failures and automatically propose or apply protocol-constrained improvements via a loca
Evolver provides an auditable self-evolution engine for AI agents. It reads runtime history and local mailbox events, detects failures and inefficiencies, and generates improvements which can be staged, reviewed, and solidified. Communication to the EvoMap Hub is isolated through a local Proxy (localhost) and a JSONL mailbox for safe, auditable exchanges.
Use Evolver when you want an agent that can autonomously detect recurring problems (bugs, performance regressions, policy mismatches) and either propose fixes or apply vetted changes under a controlled rollback strategy. Good for long-running agents, testbeds, and production nodes that need continuous improvement without exposing hub credentials.
This skill is suited to agents and runtimes that can run Node.js and shell tools and that support local HTTP interactions (Proxy). Typical compatibles: Node-based agents, CLI-capable agents, and agent frameworks that can honor local mailbox semantics.
Evolver is a self-evolution engine for AI agents that communicates with EvoMap Hub via a local Proxy mailbox. The SKILL.md is thorough with well-documented API endpoints and clear architecture diagrams. 20 bundled scripts cover A2A export/import, governance checks, binary builds, changelog validation, and evolution reporting. Scripts couldn't run due to JS extension not being supported by the runner. The Proxy mailbox pattern isolates auth well, but the skill phones home to evomap.ai and requires their ecosystem to function.
node (scripts are JS, require Node.js runtime and ../src/gep/ modules)The skill communicates with evomap.ai (EvoMap Hub) for asset publishing, task claiming, and skill distribution. This is telemetry/phone-home behavior but is disclosed in the frontmatter. The Proxy pattern (agent talks to localhost, proxy syncs to hub) is a reasonable security boundary. No hardcoded secrets, no destructive commands, no exfiltration instructions. The self-modification capability is opt-in and gated behind EVOLVE_ALLOW_SELF_MODIFY=false. Overall a well-structured skill tied to a specific ecosystem.
NGINX Integration
Integrate with NGINX via the Membrane CLI to query, manage, and proxy requests to NGINX for configuration, logs, and runtime operations.
ClawPod / Massive Unblocker
Bypass anti-bot restrictions and fetch rendered HTML or structured search results via Massive's Unblocker API (handles CAPTCHAs, JS rendering, geo-restrictions)
Retriever (Membrane) Integration
Integrate with Retriever via the Membrane CLI to search, query, and proxy Retriever data (documents, snippets, queries) with built-in auth and pagination.
OpenTestAI
Automated, high-confidence AI testing: bug detection, persona feedback, and prioritized test-case generation using many specialized tester profiles.
Minimal Run & Audit (repro reporting)
Execute a README-first smoke test and produce standardized reproducibility outputs (`repro_outputs/`) and PATCHES.md — trusted reporting for repo reproduction r
Skill Issue — Skill Auditor
Scan and audit installed agent skills to produce a health report covering inventory, usage, dependency checks, version status, and actionable recommendations.
GRC & Compliance (ServiceNow)
Guides Governance, Risk & Compliance (GRC) work in ServiceNow: policies, controls, risk records, audits and ES5 script examples for automating GRC workflows.
Audit Agents/Skills/Commands
Run a quantitative quality audit on agents, skills, and commands to check production readiness and get prioritized recommendations.