Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
codmir
MCP serversAI-powered task execution, tickets, sprints, error debugging, and desktop control.
@codmir/mcp@0.2.2 -
tokencast
MCP serversPre-execution cost estimation for LLM agent workflows with calibration learning
tokencast@0.1.1 -
trace-forge
MCP serversStructured execution trace and span logging for AI agents
trace-forge-mcp@0.1.1 -
looppause
MCP serversLoopPause MCP server — pause agent execution and route human approval requests
@looppause/mcp@0.2.1 -
QAE Safety Certification
MCP serversDeterministic pre-execution safety certification for autonomous AI agents.
qae-safety@0.1.2 -
revenueos
MCP serversSelf-hosted revenue department: find opportunities, execute approved work, measure results.
revenueos@0.2.4 -
undo-mcp
MCP serversReversibility intelligence — check if actions can be undone before executing them.
@agentutil/undo-mcp@1.0.0 -
VoxOdds
Public APIsPolymarket and Kalshi odds, all-in executable quotes, EV checks and audited forecast scores
-
occultron
MCP serversCrypto-paid uncensored LLM inference with signed execution receipts. No account.
ghcr.io/luckyjupiter/occultron-mcp:0.1.0 -
PriorSeal
MCP serversBounded authorization and independently verifiable execution evidence for agents.
-
ssis-mcp
MCP serversSSIS MCP: parse DTSX packages, validate executables, connections and variables.
@mrfentmen/ssis-mcp@1.0.1 -
CONTINUUM
MCP serversCONTINUUM: Verifiable semantic recovery for long-running AI agents. Semantic checkpoints (not conversation dumps), an idempotent action ledger that refuses duplicate side effects, and a hash-chained tamper-evident event log, all exposed as a deny-by-default MCP server. Framework-agnostic, Python 3.11+
git clone https://github.com/Cyrax321/CONTINUUM.git -
covert-coder
Tools & appsCovert Coder — a local-first sovereign AI development environment for governed models, workflows, execution, evidence, and verification.
git clone https://github.com/AnonymousNomad/covert-coder.git -
box
AI repositoriesRun AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with default-deny Dogwood policies and credential injection that keeps secrets outside the agent. Written in Rust. Supports macOS on Apple silicon and Linux.
git clone https://github.com/strands-agents/box.git -
Aegis
Agents & frameworksWindows-first desktop oversight for AI agents: live monitoring, local security reviews, token usage, audit reports and opt-in action policies/MCP gateways. Experimental Hyper-V guest execution; macOS/Linux experimental.
git clone https://github.com/antropos17/Aegis.git -
Fodda Earnings Intelligence
MCP serversCross-company earnings trends & executive divergence with citable sources.
-
InfraPulse
MCP serversAI agent infrastructure for discovery, authorization, execution, identity, and signed receipts.
-
Sato Kit
MCP serversPrepare -> execute for onchain agent actions: policy pre-flight, simulation, receipt log.
@satohub/kit@0.1.0 -
Euvra
MCP serversDiscover, compare, route, and execute machine-accessible capabilities for AI agents.
-
cucumberstudio
MCP serversMCP server for Cucumber Studio - test scenarios, action words, and execution data
cucumberstudio-mcp@1.2.2 -
Kāhea
MCP serversDeterministic HTTP/WebSocket testing and policy-gated API execution for AI agents.
https://github.com/copyleftdev/kahea/releases/download/v0.3.1/kahea-mcp-Linux-X64.mcpb -
soma
MCP serversExecution-verified code generation and verification with signed, offline-checkable certificates.
soma-verify-mcp@0.1.0 -
vssh
MCP serversSSH tunnel and remote server management MCP — execute commands, transfer files, manage
-
Apiosk Connect
MCP serversDiscover, pay for, execute, and publish APIs through Apiosk.
@apiosk/mcp@1.7.0
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.