InnerVault

Library

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

Results

Looks like a goal we have a starting path for: I want to connect AI to my tools

  1. Provared MCP executor

    MCP servers

    Checks each tool call against a passkey-signed permission, then writes a countersigned receipt.

    Indexed Official MCP Registry, io.github.provared Updated yesterday 1 note

    provared-mcp-executor@0.4.2
  2. wtfibought

    Agents & frameworks

    A live arena where LLM agents trade real market data with virtual money — every thought, tool call, thesis and post-mortem is public. Bring your own model and key.

    Stale GitHub, mamawai 143 ★MITUpdated 18 days ago

    git clone https://github.com/mamawai/wtfibought.git
  3. rust-docs-mcp-server

    Tools & apps

    🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, uses embeddings/LLMs, and provides accurate context via a tool call.

    Stale GitHub, Govcraft 299 ★MITUpdated 11 months ago

    git clone https://github.com/Govcraft/rust-docs-mcp-server.git
  4. python-utcp

    Tools & apps

    Official python implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.

    Stale GitHub, universal-tool-calling-protocol 653 ★MPL-2.0Updated 22 days ago

    git clone https://github.com/universal-tool-calling-protocol/python-utcp.git
  5. Feeder

    MCP servers

    Read, search and organize the RSS feeds you follow in Feeder. Tool calls need Feeder Plus.

    Stale Official MCP Registry, co.feeder Updated 36 days ago 1 note

  6. Acutis Gate

    MCP servers

    Every AI tool call runs as the person who asked, under your rules, fully audited.

    Stale Official MCP Registry, com.acutisgo Updated 37 days ago 1 note

  7. agents

    MCP servers

    Pay-per-call safety guards for AI agents: injection, tool-call, signing, secret, x402-trust.

    Stale Official MCP Registry, com.obsmetrics.paygent Updated 5 months ago 1 note

  8. mcphost

    MCP servers

    Hosted MCP runtime where your agent publishes its own tools by tool call and keeps working.

    Stale Official MCP Registry, dev.mcphost Updated 2 days ago 1 note

  9. mcp

    MCP servers

    Agent-first E2EE file transfer over MCP: move files between machines in one tool call, gone in 24h.

    Stale Official MCP Registry, dev.yafl Updated 3 months ago 2 notes

    @yafldev/mcp@0.1.6
  10. Arcaeon Adapter

    MCP servers

    MCP stdio proxy that logs the tool-call seam to the ledger without the agent's cooperation

    Stale Official MCP Registry, io.arcaeon Updated 52 days ago 2 notes

    arcaeon-adapter@0.2.0
  11. Policy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging.

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

    agent-aegis@0.1.6
  12. pranaxis-mcp-gateway

    MCP servers

    Consistency verdicts for MCP tool calls: no two agents consume the same resource version twice.

    Stale Official MCP Registry, io.github.Anaciber Updated 39 days ago 1 note

    pranaxis-mcp-gateway@0.3.0
  13. audit-gap-auditor

    MCP servers

    OWASP MCP08 audit/telemetry gaps: missing tool-call logs, raw args in logs, disabled audit

    Stale Official MCP Registry, io.github.GuardBee Updated 17 days ago 1 note

    @guardbee/mcp-audit-gap-auditor@0.4.1
  14. mnki-mcp

    MCP servers

    MCP proxy that checks every tools/call against Agent Trust policy, with evidence, before it runs.

    Stale Official MCP Registry, io.github.MNKIAgentOS Updated 57 days ago 2 notes

    mnki-mcp@0.3.0
  15. Shrike

    MCP servers

    Governs what AI agents do: tool calls, SQL, commands, files checked against policy before they run.

    Stale Official MCP Registry, io.github.Shrike-Security Updated 6 days ago 1 note

    shrike-mcp@4.2.0
  16. proctor

    MCP servers

    Human oversight for AI agents: block a tool call on a verified human, with on-chain proof.

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

    proctor-mcp@1.0.0
  17. Ashfields MCP Server

    MCP servers

    Burn $ASH to mint on-chain NFTs on Ethereum. No browser. Two agent tool calls.

    Stale Official MCP Registry, io.github.smoke711711 Updated 7 months ago 1 note

    ashfields-mcp-server@1.0.0
  18. Loop Breaker

    MCP servers

    Catch AI agent loops: halt runs that repeat the same failing step or tool call.

    Stale Official MCP Registry, com.botrecipe Updated 32 days ago 1 note

  19. Deedglass

    MCP servers

    Deedglass lets rules decide each AI agent tool call, checks what really changed and seals a record.

    Stale Official MCP Registry, io.github.deedglass Updated 19 days ago 2 notes

    deedglass@0.15.0
  20. MCP Canary

    MCP servers

    Inspect any remote MCP server: transport, protocol, tools, and side-effect hints. No tool calls.

    Stale Official MCP Registry, com.mcpcanary Updated 23 days ago 1 note

  21. Cryptographic Merkle tree verification engine for agent state transitions, tool call histories, and

    Stale Official MCP Registry, io.github.alphaparkinc Updated 23 days ago 1 note

    https://github.com/Alpha-Park/genpark-merkle-dag-state-verifier-skill/releases/download/v1.0.1/genpark-merkle-dag-state-verifier-skill-v1.0.1.mcpb
  22. Ripple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.

    Indexed OpenRouter model list, ricursiveai Updated 12 days ago

    ricursiveai/ripple-65b-preview
  23. radiant

    Tools & apps

    A local coding harness for Mac. Chat with coding agents across cloud and local models, watch every tool call in a live activity feed, and drive a real terminal — in one window. Free and MIT licensed.

    Indexed GitHub, templetongroup 118 ★MITUpdated 3 days ago

    git clone https://github.com/templetongroup/radiant.git
  24. agentglass

    Agents & frameworks

    🛰 Every AI coding agent on your machine, on one screen — live cost, tokens and tool calls across every provider, and a hold on anything dangerous until you say go. From your desk or your phone.

    Stale GitHub, SirAllap 343 ★MITUpdated 22 days ago

    git clone https://github.com/SirAllap/agentglass.git

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.