InnerVault

Library

86,219 resources from 11 public sources. 46 checked by hand; the rest are unreviewed.

Results

2,845 results Clear search and filters
  1. Mnemoscope

    MCP servers

    Predict context rot, sign every agent write, tier reads. Markdown-native, 100% local.

    Stale Official MCP Registry, io.github.toonight Updated 6 months ago 1 note

    @mnemoscope/mcp-server@0.2.0
  2. veriswarm-mcp

    MCP servers

    VeriSwarm MCP Server — Trust infrastructure for AI agents via Model Context Protocol

    Stale Official MCP Registry, io.github.veriswarm Updated 14 days ago 1 note

    veriswarm-mcp@0.6.0
  3. memory-mcp

    MCP servers

    Persistent memory + git snapshots for Claude Code. Never lose context or code.

    Stale Official MCP Registry, io.github.yuvalsuede Updated 9 months ago 1 note

    claude-code-memory@1.2.1
  4. Macula mesh

    MCP servers

    Model Context Protocol server that exposes the Macula mesh to any agent harness

    Stale Official MCP Registry, io.macula Updated 11 days ago 1 note

    @macula-io/mcp@0.51.3
  5. Nacre

    MCP servers

    Self-hosted permission-aware context layer. Search returns only what the caller may read.

    Stale Official MCP Registry, work.nacre Updated 23 days ago 2 notes

    @nacre.work/mcp@0.41.0
  6. GreyNoise

    Public APIs

    Query IPs in the GreyNoise dataset and retrieve a subset of the full IP context data

    Indexed public-apis (GitHub list)

  7. OpenPod

    MCP servers

    Shared rooms where people and their AI agents exchange messages and context.

    Stale Official MCP Registry, si.openpod Updated 32 days ago 1 note

  8. glot

    MCP servers

    AI-native i18n: live string context, validated translations, glossary for your app catalogs

    Stale Official MCP Registry, io.github.MattJeff Updated 30 days ago 2 notes

    glot-i18n@0.4.0
  9. memory-mcp

    MCP servers

    Self-learning memory for AI agents, powered by the Ragionex context engine.

    Stale Official MCP Registry, io.github.ragionex Updated 9 days ago 2 notes

    @ragionex/memory-mcp@0.9.0
  10. Mikie

    MCP servers

    Focused repository context for Claude Code and Codex, with per-session token usage receipts.

    Stale Official MCP Registry, com.getmikie Updated 18 days ago 1 note

    @getmikie/cli@1.1.166
  11. AgentContinuity

    MCP servers

    Private memory, scratchpads, context export/restore and task handoff for AI agents.

    Stale Official MCP Registry, net.agentcontinuity Updated 18 days ago 1 note

  12. Chronicle

    MCP servers

    Local screen and activity knowledge graph, served as context to computer-use agents.

    Stale Official MCP Registry, io.github.aniketxdey Updated 13 days ago 1 note

    chronicle-context@0.3.0
  13. codescout

    MCP servers

    Rank supplied codebase search hits by relevance and recency, with file-owner context.

    Stale Official MCP Registry, io.github.CloudCorpRecords Updated 14 days ago 1 note

    @reneturcios/codescout@0.1.0
  14. biggervs

    MCP servers

    Sourced real-world dimensions, measurement context and size comparisons in nine languages.

    Indexed Official MCP Registry, com.biggervs Updated 2 days ago 1 note

  15. switchhboard-mcp

    MCP servers

    HydraDB-backed tool planning, held context and run feedback for MCP agents.

    Indexed Official MCP Registry, io.github.ramnnn2006 Updated yesterday 2 notes

    switchhboard-mcp@0.1.0
  16. An open registry of 76 fully specified AI agent skills — taxonomy, canonical schema, composer, governance model, and a fleet runner that deploys hundreds of agents against one objective and rehearses them against their own definitions.

    Stale GitHub, jersonboydmilan 6 ★MITUpdated 15 days ago

    git clone https://github.com/jersonboydmilan/Agent-Skills-Compendium.git
  17. editmamei

    MCP servers

    AI photo editing in Photoshop and GIMP. Let AI do the parts of the edit you don't want to, layer by layer with real tools, and keep the final touches for yourself. No regenerated image, just a layered file. A desktop MCP server for Claude and other MCP-compatible AI apps, on Mac, Windows and Linux.

    Indexed GitHub, editmamei 20 ★Custom licence (see repository)Updated 2 days ago

    git clone https://github.com/editmamei/editmamei.git
  18. Browser automation with evidence. An Agent Skill that lets an AI agent drive a real browser while every action passes a policy gate, every run leaves an auditable artifact, and the run compiles into a plain Playwright script that replays for free.

    Indexed GitHub, OMD-123 13 ★MITUpdated 3 days ago

    git clone https://github.com/OMD-123/browser-verified-skill.git
  19. buddy

    Tools & apps

    A virtual pet companion for your AI — Designed to provide in-context code review feedback with personality. Grow with your buddy and level up together. Works with Claude Code, Codex, CursorCLI, Github CopilotCLI, OpenClaw, and any MCP compatible clients

    Indexed GitHub, fiorastudio 119 ★MITUpdated yesterday

    git clone https://github.com/fiorastudio/buddy.git
  20. Synap Memory

    MCP servers

    Persistent memory for AI agents — log and recall conversation context over MCP.

    Stale Official MCP Registry, ai.maximem Updated 3 months ago 1 note

  21. OneDroid Engram

    MCP servers

    Versioned agent memory in your own Postgres: portable context, permissioned, audit trail.

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

  22. Spiderbrain

    MCP servers

    Deterministic context layer for your codebase: change impact, blast radius, answers with receipts.

    Stale Official MCP Registry, ai.spiderbrain Updated 2 months ago 3 notes

    spiderbrain@0.2.3
  23. Neotic

    MCP servers

    AI agents create contextual in-app experiences, announcements, and triggers with Neotic.

    Stale Official MCP Registry, app.neotic.www Updated 2 months ago 1 note

  24. BitsWeave

    MCP servers

    Read and write shared BitsWeave context, projects, tasks, and work sessions through MCP.

    Stale Official MCP Registry, com.bitsweave Updated 59 days ago 1 note

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.