InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

1,043 results Clear search and filters
  1. codmir

    MCP servers

    AI-powered task execution, tickets, sprints, error debugging, and desktop control.

    Stale Official MCP Registry, io.github.jobrayan Updated 5 months ago 1 note

    @codmir/mcp@0.2.2
  2. tokencast

    MCP servers

    Pre-execution cost estimation for LLM agent workflows with calibration learning

    Stale Official MCP Registry, io.github.krulewis Updated 7 months ago 1 note

    tokencast@0.1.1
  3. trace-forge

    MCP servers

    Structured execution trace and span logging for AI agents

    Stale Official MCP Registry, io.github.mdfifty50-boop Updated 6 months ago 1 note

    trace-forge-mcp@0.1.1
  4. looppause

    MCP servers

    LoopPause MCP server — pause agent execution and route human approval requests

    Stale Official MCP Registry, io.github.soteeabam Updated 3 months ago 2 notes

    @looppause/mcp@0.2.1
  5. Deterministic pre-execution safety certification for autonomous AI agents.

    Stale Official MCP Registry, io.github.tb8412 Updated 8 months ago 1 note

    qae-safety@0.1.2
  6. revenueos

    MCP servers

    Self-hosted revenue department: find opportunities, execute approved work, measure results.

    Stale Official MCP Registry, io.github.unempyd Updated 2 months ago 2 notes

    revenueos@0.2.4
  7. undo-mcp

    MCP servers

    Reversibility intelligence — check if actions can be undone before executing them.

    Stale Official MCP Registry, net.agentutil Updated 8 months ago 1 note

    @agentutil/undo-mcp@1.0.0
  8. VoxOdds

    Public APIs

    Polymarket and Kalshi odds, all-in executable quotes, EV checks and audited forecast scores

    Indexed public-apis (GitHub list)

  9. occultron

    MCP servers

    Crypto-paid uncensored LLM inference with signed execution receipts. No account.

    Stale Official MCP Registry, io.github.luckyjupiter Updated 32 days ago 1 note

    ghcr.io/luckyjupiter/occultron-mcp:0.1.0
  10. PriorSeal

    MCP servers

    Bounded authorization and independently verifiable execution evidence for agents.

    Stale Official MCP Registry, io.github.imokokok Updated 18 days ago 1 note

  11. ssis-mcp

    MCP servers

    SSIS MCP: parse DTSX packages, validate executables, connections and variables.

    Stale Official MCP Registry, io.github.mrfentmen Updated 3 days ago 1 note

    @mrfentmen/ssis-mcp@1.0.1
  12. CONTINUUM

    MCP servers

    CONTINUUM: 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+

    Stale GitHub, Cyrax321 24 ★Apache-2.0Updated 23 days ago

    git clone https://github.com/Cyrax321/CONTINUUM.git
  13. covert-coder

    Tools & apps

    Covert Coder — a local-first sovereign AI development environment for governed models, workflows, execution, evidence, and verification.

    Stale GitHub, AnonymousNomad 53 ★Apache-2.0Updated 34 days ago

    git clone https://github.com/AnonymousNomad/covert-coder.git
  14. box

    AI repositories

    Run 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.

    Indexed GitHub, strands-agents 544 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/strands-agents/box.git
  15. Aegis

    Agents & frameworks

    Windows-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.

    Stale GitHub, antropos17 158 ★MITUpdated 20 days ago

    git clone https://github.com/antropos17/Aegis.git
  16. Cross-company earnings trends & executive divergence with citable sources.

    Stale Official MCP Registry, ai.fodda Updated 2 months ago 1 note

  17. InfraPulse

    MCP servers

    AI agent infrastructure for discovery, authorization, execution, identity, and signed receipts.

    Stale Official MCP Registry, ai.infrapulse Updated 2 months ago 1 note

  18. Sato Kit

    MCP servers

    Prepare -> execute for onchain agent actions: policy pre-flight, simulation, receipt log.

    Stale Official MCP Registry, ai.satohub Updated 48 days ago 1 note

    @satohub/kit@0.1.0
  19. Euvra

    MCP servers

    Discover, compare, route, and execute machine-accessible capabilities for AI agents.

    Stale Official MCP Registry, dev.euvra Updated 47 days ago 1 note

  20. cucumberstudio

    MCP servers

    MCP server for Cucumber Studio - test scenarios, action words, and execution data

    Stale Official MCP Registry, io.github.HeroSizy Updated 7 months ago 1 note

    cucumberstudio-mcp@1.2.2
  21. Kāhea

    MCP servers

    Deterministic HTTP/WebSocket testing and policy-gated API execution for AI agents.

    Stale Official MCP Registry, io.github.copyleftdev Updated 3 months ago 1 note

    https://github.com/copyleftdev/kahea/releases/download/v0.3.1/kahea-mcp-Linux-X64.mcpb
  22. soma

    MCP servers

    Execution-verified code generation and verification with signed, offline-checkable certificates.

    Stale Official MCP Registry, io.github.medianemi-beep Updated 2 months ago 2 notes

    soma-verify-mcp@0.1.0
  23. vssh

    MCP servers

    SSH tunnel and remote server management MCP — execute commands, transfer files, manage

    Stale Official MCP Registry, io.github.meshpop Updated 8 months ago

  24. Apiosk Connect

    MCP servers

    Discover, pay for, execute, and publish APIs through Apiosk.

    Stale Official MCP Registry, io.github.obcraft Updated 3 months ago 3 notes

    @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.