Install payload
Install payload is broadly covered in current results.
100% (12/12)
Source-backed filter active — add entries to compare trust side by side.
Trust signals across 40 of 101 results
3 trust signals differ in this sample: Review status, Source provenance, Submitter
Signals differ on Review status, Source provenance, Submitter — add entries to compare before you install.
Rollout signal scan
Biggest gaps: metadata review, package integrity. 0 entries have 2+ required gaps.
Install payload
Install payload is broadly covered in current results.
100% (12/12)
Most at-risk entries in this view
Adoption queue
3/101 visible results are in hold tier and need mitigation before adoption.
No required blockers for this preset.
64/100
Collect package checksum or signed artifact information.
mcp/packrift-mcp-server · trust review · confidence 83%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
mcp/adyen-mcp-server · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
mcp/aws-serverless-mcp-server · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
mcp/azure-mcp-server · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
mcp/basic-memory-mcp-server · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
mcp/blender-mcp-server · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
mcp/brave-search-mcp-server · trust review · confidence 67%
1 blockers: Metadata review
50/100
Request metadata review from maintainers or internal owners.
Collect package checksum or signed artifact information.
mcp/ai-butlerbrain-mcp-mcp-server · trust review · confidence 67%
Decision confidence
3/101 results are low-confidence and need review before adoption.
Address Package integrity before broader rollout.
68/100
mcp/packrift-mcp-server · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
mcp/adyen-mcp-server · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
mcp/aws-serverless-mcp-server · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
mcp/azure-mcp-server · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
mcp/basic-memory-mcp-server · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
mcp/blender-mcp-server · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
mcp/brave-search-mcp-server · trust review
Address Metadata review, Package integrity before broader rollout.
54/100
mcp/ai-butlerbrain-mcp-mcp-server · trust review
Freshness distribution
Median age 40 days; all 12 scanned entries are within 90 days.
Theme distribution
98 distinct themes with no dominant one. Most common: mcp, developer-tools, claude-code.
98 distinct themes across 24 scanned
MIT-licensed Agent Skills collection for context engineering, harness engineering, multi-agent architectures, filesystem context, memory systems, tool design, evaluation, hosted agents, and production agent operating loops for Claude Code, Cursor, Codex, and Open Plugins-compatible agent tools.
Community reusable agent prompt for recovering Claude Code sessions after auto-compaction or context thrashing using official context-window docs: rebuild goals from git, validate tasks, and block destructive edits after memory loss.
MCP server for context-window optimization that routes large tool outputs through sandbox tools, indexes session state, and helps agents retrieve only the context they need.
MCP server for semantic codebase intelligence, combining AST structure, embeddings, clustering, feature hubs, restore points, and memory graph tools.
Context7 MCP server by Upstash that pulls up-to-date, version-specific library documentation and code examples directly into Claude's context so answers match the libraries you actually use.
Packrift MCP Server exposes Packrift's packaging-supplies catalog through a remote MCP endpoint. It lets AI agents search packaging products, retrieve pricing and inventory context, and create cart URLs for ecommerce packaging workflows.
Token-efficient MCP server for source-code exploration that indexes codebases with tree-sitter, then lets agents retrieve symbols, file outlines, dependency context, blast radius, dead code, PR risk, and targeted source snippets instead of reading whole files.
Official C# SDK for Model Context Protocol servers and clients, maintained by the MCP project in collaboration with Microsoft, with NuGet packages for core MCP APIs, hosting and dependency injection extensions, ASP.NET Core HTTP servers, samples, API documentation, and cross-application access support.
Official Go SDK for Model Context Protocol servers and clients, maintained by the MCP project in collaboration with Google, with packages for MCP, JSON-RPC, OAuth primitives, OAuth protected-resource metadata, clients, servers, transports, examples, and conformance work.
Official TypeScript SDK for Model Context Protocol clients and servers, with the production v1 `@modelcontextprotocol/sdk` package, active v2 server and client package work, Node.js, Bun, and Deno support, transports, OAuth helpers, tools, resources, prompts, examples, and API documentation.
MIT-licensed Agent Skill for persistent file-based planning across Claude Code, Codex, Cursor, Gemini CLI, OpenCode, Hermes Agent, OpenClaw, Kiro, and other SKILL.md-compatible coding agents, with task_plan.md, findings.md, progress.md, hooks, session recovery, attestation, and opt-in long-running run modes.
Open-source RAG and agentic retrieval platform with DeepDoc document understanding, visual chunking, grounded citations, heterogeneous data-source ingestion, agent workflows, MCP support, code executor support, and Docker self-hosting.
Expert Claude Code context window audit capability pack for measuring what loads at session start, what each read and extension adds, when compaction drops path-scoped rules, and how to delegate or compact before quality drops.
Official CircleCI MCP server that lets LLMs query build and test failures, detect flaky tests, check pipeline status, fetch build logs, and validate config in CircleCI through natural language.
MCP server and Blender add-on that let Claude inspect scenes, create and modify 3D objects, run Blender Python, capture viewport screenshots, and use asset or 3D-generation integrations from inside Blender.
Official Brave Search MCP server for giving Claude web, local, place, image, video, news, LLM context, and summarizer search tools backed by the Brave Search API.
Stdio MCP server that lets Claude ask the Google Gemini CLI for large-file, codebase, brainstorming, and sandboxed analysis while preserving MCP tool and prompt workflows inside Claude Code or compatible MCP clients.
MCP server for GPT Researcher that gives Claude deep research, quick search, report writing, source retrieval, research context, and research-resource tools backed by web search and LLM providers.
Open-source MCP gateway, registry, and proxy from IBM that federates MCP servers, A2A agents, REST APIs, and gRPC services behind centralized discovery, governance, authentication, observability, and admin controls.
Local-first context-engineering MCP server and CLI that gives Claude token-efficient file reads, shell-output compression, code search, graph queries, persistent session memory, context packaging, verification tools, and dashboard-style token accounting through a single Rust binary.
MCP server and CLI toolkit that indexes local code into a graph database so Claude can query functions, call chains, dependencies, and repository structure.
Terminal-based agentic AI coding assistant from Charm that works with many LLM providers, uses LSP and MCP for context, manages per-project sessions, and asks permission before running tools by default.
Official dbt Labs MCP server that gives AI agents context from dbt Core, dbt Fusion, dbt Platform, project metadata, SQL tools, lineage, Admin API, and dbt documentation search.
Framelink MCP server that gives AI coding agents simplified Figma layout, styling, and design context for implementing Figma frames in code.
Local-first context compression MCP server for reducing tool outputs, logs, files, RAG chunks, and agent context before they reach the model.
Open-source project behind CodeLayer, an IDE for orchestrating AI coding agents built on Claude Code, with keyboard-first workflows, team context engineering, and parallel Claude Code sessions across worktrees and cloud workers.
JADX plugin and companion Python MCP server that lets Claude inspect, search, refactor, and debug decompiled Android APKs from JADX-GUI.
Expert skill for reviewing Playwright trace artifacts, screenshots, action timelines, network events, retries, and CI evidence to classify flaky browser test failures without guessing from logs alone.
PreToolUse hook that scans proposed writes to prompt, agent, rule, markdown, and context files for common prompt-injection phrases before the content is saved into an AI-readable surface.
Official Microsoft Azure MCP server that connects Claude and other MCP clients to Azure subscriptions, resource groups, storage, databases, Key Vault, Monitor, App Service, AKS, AI Search, Cosmos DB, RBAC, pricing, and other Azure services through local stdio or self-hosted HTTP transports.