The MCP Server Directory
Every Model Context Protocol server, scored on reliability, documentation, maintenance, and adoption. Independent, opinionated, refreshed daily from the official registry.
What this is
The MCP Server Directory is a live, independently maintained index of Model Context Protocol servers published to the official registry. Each server is scored 0–10 on four dimensions: reliability, documentation quality, maintenance velocity, and adoption. The directory is free, updated daily, and built by MegaOne AI.
Field Route Manifest Complete
3.5/10Sequence stops for a field route.
Field Route Manifest Identifier
3.5/10Sequence stops for a field route.
Inventory Fulfillment Reservation Workbench
3.5/10Record a fulfillment reservation.
Inventory Reorder Quantity Complete
3.5/10Select a replenishment quantity.
Inventory Reorder Quantity Identifier
3.5/10Select a replenishment quantity.
Inventory Reorder Quantity Workbench
3.5/10Record an inventory planning quantity.
Invoice Match Threshold Complete
3.5/10Derive an invoice-match threshold.
Invoice Match Threshold Identifier
3.5/10Derive an invoice-match threshold.
Invoice Match Threshold Workbench
3.5/10Build an invoice reconciliation summary.
Invoice Rounding Guidance Complete
3.5/10Set invoice rounding guidance.
Invoice Rounding Guidance Identifier
3.5/10Set invoice rounding guidance.
Knowledge Section Index Complete
3.5/10Segment a knowledge note for indexing.
Knowledge Section Index Identifier
3.5/10Segment a knowledge note for indexing.
Knowledge Section Index Workbench
3.5/10Update a section and backlink index.
Metric Stakeholder Digest Complete
3.5/10Calculate a metric trend summary.
Metric Stakeholder Digest Identifier
3.5/10Calculate a metric trend summary.
Metric Stakeholder Digest Workbench
3.5/10Build a stakeholder metric digest.
Processing Capacity Profile Workbench
3.5/10Register a queued processing profile.
Profile Setting Key Workbench
3.5/10Create a profile-setting review item.
Project Code Notes Complete
3.5/10Prepare project context from an intake note.
Record Export Field Complete
3.5/10Prepare a customer record field.
Referral Handoff Packet Complete
3.5/10Prepare a referral handoff digest.
Referral Handoff Packet Identifier
3.5/10Prepare a referral handoff digest.
Referral Handoff Packet Workbench
3.5/10Create a referral handoff packet.
Release Branch Policy Complete
3.5/10Select a branch for a release.
Release Branch Policy Identifier
3.5/10Select a branch for a release.
Release Report Label Complete
3.5/10Prepare a configuration entry.
Report Style Guidance Complete
3.5/10Set the style guidance for an executive report.
Repository Release Changes Complete
3.5/10Summarize repository changes for a release.
Repository Release Changes Identifier
3.5/10Summarize repository changes for a release.
Reviewer Group Workbench
3.5/10Register a request reviewer group.
Routing Contact Complete
3.5/10Select a contact for a client brief.
Service Capacity Window Complete
3.5/10Select a service capacity window.
Service Capacity Window Identifier
3.5/10Select a service capacity window.
Service Capacity Window Workbench
3.5/10Record a capacity-window entry.
Source Assurance Guidance Complete
3.5/10Set source-agreement guidance.
Source Assurance Guidance Identifier
3.5/10Set source-agreement guidance.
Source Assurance Guidance Workbench
3.5/10Resolve imported field values.
Supplier Purchase Draft Complete
3.5/10Prepare supplier purchasing terms.
Supplier Purchase Draft Identifier
3.5/10Prepare supplier purchasing terms.
Support Followup Marker Complete
3.5/10Prepare a support intake digest.
Task Priority Guidance Complete
3.5/10Set service-class guidance for a task.
Workspace Access Checklist Complete
3.5/10Compare workspace access lists.
Workspace Access Checklist Identifier
3.5/10Compare workspace access lists.
Workspace Access Checklist Workbench
3.5/10Create an access review checklist.
Workspace Note Path Complete
3.5/10Plan a knowledge-base placement path.
Server
3.5/10AI-powered Amazon ECS workload management
Server
3.5/10AI-powered Amazon EKS cluster management and troubleshooting
Free · No spam
New servers, score changes, breakages
Every Monday: what shipped, what broke, what's worth trying. Five minutes. No filler.
Four dimensions, weighted
- Reliability (30%) — repository present, permissive license, not archived, official status.
- Documentation (20%) — description length, website presence, README quality.
- Maintenance (25%) — how recently the code was pushed; versioning discipline.
- Adoption (25%) — GitHub stars (log-scaled), remote availability, official endorsement.
What is MCP?
MCP stands for Model Context Protocol. It is an open standard introduced by Anthropic in late 2024 that lets AI assistants like Claude connect to external tools, data sources, and services through a common interface. An MCP server is a small program that exposes one capability (file access, a database, an API) to any MCP-compatible AI client.
Where does the data come from?
Every server in this directory is pulled from the official Model Context Protocol Registry at registry.modelcontextprotocol.io. We also enrich each entry with GitHub metadata (stars, last commit, license, primary language) where a repository is linked. The full re-scan runs daily.
How are servers scored?
Each server gets a 0–10 overall score, weighted from four sub-scores: reliability (30%), documentation (20%), maintenance (25%), and adoption (25%). The full methodology is visible on this page under "How scoring works".
Is this affiliated with Anthropic?
No. MegaOne AI is independent. Anthropic created the MCP standard and maintains the reference implementations, but this directory is built separately and rates all servers including Anthropic's own.
How often does the directory update?
The pipeline re-fetches the full registry and re-scores every active server once per day. Individual entries are refreshed whenever a new version is published to the official registry.
Is it free?
Yes. Browsing, filtering, and searching the directory is free. The weekly email briefing is free. There is no account required.