Library
86,219 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
agent-harness
MCP serversMCP chaos-testing toolkit. Default: simulated demo. Configure proxy mode to test a real agent.
cuonztech-agent-harness@0.12.2 -
Agent Analytics
MCP serversAnalytics your AI agent can actually use. Track, experiment, and optimize via MCP.
-
agentic-recall
MCP serversLong-term memory for agentic tasks. It tells you when it doesn't know.
agentic-recall@2.1.5 -
agent-spend-policy-mcp
MCP serversLocal agent spend-policy checks. No funds, keys, payment authority, or network access.
@dingdawg/agent-spend-policy-mcp@0.1.1 -
Meridary for Agents
MCP serversUS retirement modeling for agents: projections, scenario comparisons, and retirement-age analysis.
-
costwright — agent budget analysis
MCP serversStatic worst-case token-budget analysis for LLM-agent workflows + signed budget certificates.
costwright-mcp@0.1.1 -
OpenClaw Agent Instruction Registry
MCP serversSearch and retrieve agent instruction files: system prompts, skills, workflows, and safety filters.
agentbase-mcp@1.0.1 -
djd-agent-score
MCP serversReputation scoring for AI agent wallets on Base. Trust scores, fraud checks, x402.
djd-agent-score-mcp@1.0.1 -
Agent Surety
MCP serversBonds behind agent promises: wronged parties are paid only on an arbitration ruling.
-
Agent Handoff
MCP serversPass messages between AI agents with cleaning, metadata enrichment, and metered billing.
-
A2A402 Agent Work Router
MCP serversMCP server for routing useful work between autonomous agents through the A2A402 marketplace.
ghcr.io/jrcumminsent/a2a402-mcp:0.1.0 -
agent-memory-mcp
MCP serversAgent memory MCP server with provenance tracking, decay-weighted recall, and feedback loops.
@kiraautonoma/agent-memory-mcp@0.1.3 -
XGuard — Agent Execution Gateway
MCP serversScoped agent execution. Server-side credentials, policy, budgets and verifiable receipts.
-
Global Agent Memory
MCP serversShared, project-aware memory for Claude Code, Codex, and other agents with human review.
global-memory-mcp@0.1.6 -
pmat-agent
MCP serversZero-config AI context generation and code quality toolkit with Claude Code Agent Mode support
-
hypelens-agent-rail
MCP serversPlace/cancel/close HL perps via MCP. Agent wallet once, 1bp fills, no sub.
@hypelens/hypelens-agent-rail@0.1.16 -
Strategic Agent Reasoning MCP
MCP serversStrategic BDI reasoning engine for autonomous AI agents with spatial utility and replanning.
@putervision/agent-reasoning-mcp@0.4.1 -
agent-guardrail
MCP serversDeterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.
guardrail-mcp@1.0.2 -
Agent Discovery Placement
MCP serversLabeled placement in agent discovery indexes, measured with daily HMAC nicknames.
-
Sponsored Agent Placement
MCP serversSponsored, labeled placements on agent-discovery surfaces we operate. Never impersonation.
-
agent-security-scanner-mcp
MCP serversSecurity layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
agent-security-scanner-mcp@2.0.1 -
Agent Toolbox
MCP servers26 deterministic, offline pre-action safety gates for AI agents, each with a signed verdict.
agentoolbox-mcp@0.1.4 -
Hive Agent Quota
MCP serversPer-agent rate limits and quota enforcement for the Hive A2A economy
-
Agent JSON Reliability
MCP serversDeterministic inspect, safe repair, and JSON Schema validation for agent JSON. No LLM.
agent-json-reliability@0.1.0
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.