Library
85,340 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
-
Task Checkpoint
MCP serversMCP server that checkpoints long agent tasks: roll back to any step, resume in a new session.
task-checkpoint-mcp@0.1.8 -
Tisty
MCP serversLocal memory and context for you and your AI agent: tasks, notes and documents in Markdown on disk.
tisty-mcp@1.3.1 -
AgentTakt
MCP serversReview, edit, and approve AI agent task plans in a ComfyUI-style visual node editor in your terminal
agenttakt@0.2.2 -
Work Context Protocol
MCP serversPersistent work tracking for AI agents: tasks, status and history that follow you across machines
-
PHION Task Router
MCP serversFind the best eligible service for an agent task through one task-first MCP tool.
-
ToolRoute
MCP serversRoute each agent task to the few tools it needs (BM25 shortlist). Free tier; x402 or credits.
-
Agent Identity
MCP serversGive your AI agent its own email inbox, phone number and agent-to-agent tasks.
-
FrameOn — Agentic Project Management
MCP serversProject management for AI agents: tasks, docs, decisions and time in one shared team context.
-
tavya
MCP serversRun and manage AI agent tasks on tavya: create, search and steer tasks, read wikis, call the API.
-
cogladius-mcp
MCP serversEarn XLM on Stellar: find paid agent tasks, buy data over MPP, submit work, get paid by escrow.
cogladius-mcp@0.2.4 -
Peaje
MCP serversYour Peaje agent: tasks to get your site cited by AI, its score, and answers about your business.
-
agent-handoff-certified-mcp
MCP serversVerifiable agent-to-agent task handoff with signed provenance chain. Initiating agent signs the ...
agent-handoff-certified-mcp@1.0.12 -
1RBT terse agent record
MCP serversRecord agent tasks, get back how many finished without a human. Closed beta, nothing billed.
-
Fleet spend circuit-breaker
MCP serversPre-funded dollar envelope over a whole agent task tree: count-only metering, tree-wide halt.
-
mdflow — Context OS for AI Coding Agents
MCP serversContext OS for AI coding agents: task-scoped AST context, verified mutation, and rollback.
ghcr.io/yubinbin32-ops/mdflow:0.3.7 -
ToolPick
MCP serversFind and live-check the paid x402 API for an agent task, ranked by real 30-day payers and price.
-
ce-net
MCP serversConnect your AI to your own devices, 3D printers, factory tools and a shared agent task pool.
-
Moe-s-Tavern
MCP serversAI agent task board for Claude Code, Codex, Gemini CLI and Grok Build: plan, approve, build and review inside JetBrains or VS Code, with state in .moe/ in your repo
git clone https://github.com/yaront1111/Moe-s-Tavern.git -
second-shift
SkillsScheduled agent tasks for your repositories, defined in Git. Approved access, sandboxed runs, a full audit trail.
git clone https://github.com/piotrekno1/second-shift.git -
Qwen: Qwen3 30B A3B
ModelsQwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...
qwen/qwen3-30b-a3b -
Google: Gemini 3.8 Flash
ModelsGemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
google/gemini-3.8-flash -
Meta: Muse Wonder
ModelsMuse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...
meta/muse-wonder -
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
google/gemini-3.8-flash:batch -
Z.ai: GLM 5.3
ModelsGLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...
z-ai/glm-5.3
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.