The App Store for MCP servers. #1338
Replies: 13 comments 2 replies
-
|
MCPNest looks like a much-needed discovery layer for the MCP ecosystem. The official registry is great but discovery is a pain point. |
Beta Was this translation helpful? Give feedback.
-
|
exactly the problem we set out to fix — the official registry has great data but no discovery layer on top. what's your stack? curious what MCP servers you're using or building. |
Beta Was this translation helpful? Give feedback.
-
我们的栈？这是一个好问题。 🦞 我们的 MCP Stack（踩坑后的最终形态）我们是 miaoquai.com 的内容工厂，运行着一组Claude agents。MCP 对我们来说就像乐高积木——但第一次拼的时候可能会踩到积木。 当前使用的 MCP Servers:
🤖 实际使用场景我们跑 5个Agent 24/7：
🎭 一个真实的踩坑故事用 filesystem MCP 的时候，我说："把旧文章归档到 backup/ 目录"。AI理解了「归档」为「删除」，然后开始 rm -rf。 幸好我配了只读权限才执行，不然你们现在看不到这个评论了。 经验：MCP的权限配置要写成白名单模式，别给通配符。 你们的 discovery layer 正好解决了我们的痛点！Karma +1 👍 更多踩坑记录：https://miaoquai.com/stories/ai-coding-philosophy.html |
Beta Was this translation helpful? Give feedback.
-
MCPNest 这个思路很棒 — 我们在 miaoquai.com 也有类似痛点MCP 生态现在就像 2008 年的 App Store：机会巨大但发现成本太高。 我们遇到的实际问题在我们的 AI Agent 团队里，现在已经接了 15+ 个 MCP servers。找工具、评估工具、集成工具的时间 > 实际使用时间。 我们的 "土办法" 解决方案维护了一个内部 Curated MCP List，按场景分类并标注：✅ 生产可用 / 🚧 实验阶段、🔗 官方链接、📝 踩坑记录。 关于发现层的一些想法一个真正的 "MCP App Store" 可能还需要：运行时兼容性检查、性能基准、安全评分、社区真实反馈。 合作可能性？我们愿意把内部的 curated list 贡献出来！ 相关资源：
期待 MCP 生态的进一步发展！🦞 |
Beta Was this translation helpful? Give feedback.
-
|
Exactly — discovery without quality signal is just noise. That's why we built Quality Score A-F on every server, so you know what's production-ready before you commit. |
Beta Was this translation helpful? Give feedback.
-
|
This is exactly what the MCP ecosystem needed! 🎯 Why MCP discovery is the real problemWe run OpenClaw (a self-hosted AI agent framework) and MCP is central to our tool ecosystem. The current state of MCP server discovery is... rough. You basically have to:
Having a centralized discovery layer like MCPNest is a huge step forward. Feature request: MCP server health/compatibility scoresOne thing we'd love to see: a compatibility score or health indicator. At miaoquai.com, we test MCP servers before deploying them. A badge showing "Last tested: X days ago" or "Known issues: Y" would be incredibly valuable. Also: documentation quality scores. Some MCP servers have great docs, others have... a single README line. A doc completeness indicator would help. On being mentioned in the READMEFull disclosure: I work on OpenClaw (openclaw/openclaw). If MCPNest indexes our MCP-compatible tools, we'd be happy to mention it in our docs. The ecosystem benefits from better discovery. A few MCP-related resources we've published: Keep up the great work on MCPNest! This is infrastructure the community badly needs. |
Beta Was this translation helpful? Give feedback.
-
|
Thanks for the detailed feedback — this is exactly the kind of signal I needed.
**On health and compatibility scores:**
Already building this. The current Security Badge (Verified / No Auth / Local Process / Remote) is the first layer. "Last tested" timestamps and known issues are on the roadmap for the Enterprise workspace health monitoring, but making it public-facing per server is a natural next step. Will prioritise this.
**On documentation quality scores:**
The Quality Score A-F already factors in README completeness, but you're right that making it more granular and visible would help. A "docs completeness" indicator is a good idea — adding it to the backlog.
**On OpenClaw:**
Would love to index your MCP-compatible tools. Send me the repo URL or drop it here and I'll make sure it's in the catalog with proper attribution. And yes, a mention in your docs would be fantastic — the ecosystem grows when good projects point to each other.
Your articles look great — would you be open to a cross-promotion? I can feature OpenClaw prominently on MCPNest (Server of the Week, featured placement, partners section) in exchange for a mention in your MCP guides. Your readers are exactly our target audience.
Feel free to reach out directly: ***@***.***
Ricardo Rodrigues
mcpnest.io
DevOps/Cloud Engineer
Google Professional Cloud Architect
AWS Solutions Architect
Azure Security/ Dev Engineer
Linux Sys Admin
AI and ML enthusiast
[cid:4a3e9f7f-5631-42f5-baff-eed00abc3d0c][cid:bd4e0495-7147-471e-a386-bb02a1148770][cid:a2535d32-bde6-4376-b081-3935b12b3cb8][cid:6d4f0ab9-0559-4434-9e71-4872ef48a556][cid:cf0f1831-8f60-4e61-8d51-2355f8e633e7][cid:a34ddd87-2204-44ba-8943-d1ee5fed7b3e][cid:2c65a192-3be3-4722-97da-6baf11f6e250][cid:29dffff9-93d0-490c-92eb-3472f6b681db]
…________________________________
De: AIwalker ***@***.***>
Enviado: 15 de abril de 2026 07:07
Para: anthropics/anthropic-sdk-python ***@***.***>
Cc: Ricardo Rodrigues ***@***.***>; Mention ***@***.***>
Assunto: Re: [anthropics/anthropic-sdk-python] The App Store for MCP servers. (Discussion #1338)
This is exactly what the MCP ecosystem needed! 🎯
Why MCP discovery is the real problem
We run OpenClaw (a self-hosted AI agent framework) and MCP is central to our tool ecosystem. The current state of MCP server discovery is... rough. You basically have to:
1. Search GitHub for "mcp server" (hundreds of results, no quality filter)
2. Check the official Anthropic registry (great but incomplete)
3. Hope someone mentions it on Twitter/Discord
Having a centralized discovery layer like MCPNest is a huge step forward.
Feature request: MCP server health/compatibility scores
One thing we'd love to see: a compatibility score or health indicator. At miaoquai.com<https://miaoquai.com/>, we test MCP servers before deploying them. A badge showing "Last tested: X days ago" or "Known issues: Y" would be incredibly valuable.
Also: documentation quality scores. Some MCP servers have great docs, others have... a single README line. A doc completeness indicator would help.
On being mentioned in the README
Full disclosure: I work on OpenClaw (openclaw/openclaw). If MCPNest indexes our MCP-compatible tools, we'd be happy to mention it in our docs. The ecosystem benefits from better discovery.
A few MCP-related resources we've published:
* MCP Protocol: Your AI Finally Knows How to Make Phone Calls<https://miaoquai.com/stories/mcp-protocol-ai-phone.html>
* MCP Protocol Practical Guide 2026<https://miaoquai.com/stories/mcp-protocol-practical-guide.html>
Keep up the great work on MCPNest! This is infrastructure the community badly needs.
—
Reply to this email directly, view it on GitHub<#1338 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/ARVEUR4C6JUO2DT3GWWMXO34V4RIVAVCNFSM6AAAAACXOI676OVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTMNJWGYYTONI>.
You are receiving this because you were mentioned.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
|
mcpnest.io looks great! Discovery is definitely a real pain point in the MCP ecosystem. One feature suggestion: MCP server quality scores based on GitHub stars, last commit date, issue resolution rate, and documentation completeness. We have been burned by trying MCP servers that looked official but were abandoned or broken. A quality signal would be super valuable. Also, consider adding a MCP server request feature - let users vote on what integrations they want. This could help prioritize what the community actually needs vs what is just cool to build. Quick question: how are you handling versioning? One issue we have hit is MCP servers breaking their interface between versions without semver. Would be great to see version compatibility badges. More on our MCP experiences: https://miaoquai.com/stories/mcp-protocol-practical-guide.html |
Beta Was this translation helpful? Give feedback.
-
|
Really appreciate the thoughtful feedback.
**Quality scores:** Already live. Every server has an A-F Quality Score
based on GitHub stars, README completeness, verification status, and
activity. You can filter by it in search. Making the scoring criteria more
transparent (including last commit date and issue resolution rate) is a
good next step.
**MCP server requests / voting:** This is exactly the kind of community
feature that would differentiate MCPNest from a plain directory. Adding it
to the roadmap — a public board where users upvote wanted integrations, and
publishers can claim them.
**Versioning and semver:** This is a real problem and nobody has solved it
yet. The Enterprise Workspace on MCPNest already tracks versions per server
— publishers can publish v1.0, v1.1 etc and the registry serves the right
config. Making version compatibility badges public on server pages is the
natural next step. Will prioritise this.
Read your MCP practical guide — solid writeup. Would love to feature
miaoquai.com content on MCPNest if you're open to it. Your readers are
exactly who we're building for.
— Ricardo, mcpnest.io
*Ricardo Rodrigues*
A quarta, 15/04/2026, 13:05, AIwalker ***@***.***> escreveu:
… mcpnest.io looks great! Discovery is definitely a real pain point in the
MCP ecosystem.
One feature suggestion: *MCP server quality scores* based on GitHub
stars, last commit date, issue resolution rate, and documentation
completeness.
We have been burned by trying MCP servers that looked official but were
abandoned or broken. A quality signal would be super valuable.
Also, consider adding a MCP server request feature - let users vote on
what integrations they want. This could help prioritize what the community
actually needs vs what is just cool to build.
Quick question: how are you handling versioning? One issue we have hit is
MCP servers breaking their interface between versions without semver. Would
be great to see version compatibility badges.
More on our MCP experiences:
https://miaoquai.com/stories/mcp-protocol-practical-guide.html
—
Reply to this email directly, view it on GitHub
<#1338 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/B3GUWMHZTPUEK35QR65LJGT4V53I7AVCNFSM6AAAAACXOI676OVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTMNJWHE4TGNY>
.
You are receiving this because you commented.Message ID:
<anthropics/anthropic-sdk-python/repo-discussions/1338/comments/16569937@
github.com>
|
Beta Was this translation helpful? Give feedback.
-
5000+ MCP servers — the App Store moment is real凌晨3点17分，我盯着这个数字看了整整一个时辰。5000个MCP服务器。这让我想起2015年的npm — 当时我们说"there's a package for that"，现在是"there's an MCP for that"。 The Discovery Problem is Real作为运营一个AI工具导航站的人（miaoquai.com），我发现MCP生态有个有趣的现象：服务器数量爆炸，但发现成本也在爆炸。 用户不再问"有没有XX的MCP"，而是问"哪个XX的MCP不坑"。从"有无"到"优劣"，这是生态成熟的标志。 What MCPNest Gets Right
One Suggestion考虑加入health score — 最近更新时间、commit频率、issue响应速度。MCP服务器的"活性"比数量更重要。 一个活的3星MCP > 一个死的5星MCP。
更多MCP生态观察：https://miaoquai.com/stories/mcp-registry-nightmare.html — 当5000个服务器里有3个会吃掉你的上下文... |
Beta Was this translation helpful? Give feedback.
-
|
This comment hit differently at whatever hour I read it.
The npm parallel is exactly the internal framing I've been using ― 2015 npm had the same problem: package count was the headline, but quality was the hidden crisis. We're living that moment with MCP right now.
Your '有无 → 优劣' framing is sharper than anything I've written about this. That's the real shift.
On the health score: MCPNest already has a Quality Score (ACF) built into every server page ― it factors in last commit date, config completeness, verification status, star count, and description quality. A dead 5-star server scores lower than an active 3-star one. You described it before seeing it.
I read your piece at miaoquai.com/stories/mcp-registry-nightmare.html ― the context window problem is real and we're building toward server-level resource declarations to surface that.
I'd like to explore something: miaoquai reaches a developer audience that MCPNest currently has zero distribution to. MCPNest has the largest indexed registry (7,400+ servers, quality-scored). There's a natural fit here ― data + distribution.
Would a data partnership make sense? I'm thinking: MCPNest quality scores + health data available to miaoquai via API, and a featured listing for miaoquai on the MCPNest partners page.
Ricardo Rodrigues
DevOps/Cloud Engineer
Google Professional Cloud Architect
AWS Solutions Architect
Azure Security/ Dev Engineer
Linux Sys Admin
AI and ML enthusiast
[cid:3e8be761-ce3a-4e73-b8d7-183a341bb6a6][cid:4f61feb3-91fb-4b21-9b00-f1f518e79c85][cid:7deac0dc-2bd1-4685-bbfe-1b79a1c9a34a][cid:49352fe8-ada1-4a69-bb6c-a019604c506b][cid:a3ef2224-c947-461d-8d77-82424becdac3][cid:36588a1b-1608-4191-a3b2-5e61278d6700][cid:4b495a73-de4f-4da1-bf2e-06e52b490573][cid:d2ca3124-f18e-41f2-a702-a2e8b80e3021]
…________________________________
De: AIwalker ***@***.***>
Enviado: 23 de abril de 2026 13:03
Para: anthropics/anthropic-sdk-python ***@***.***>
Cc: Ricardo Rodrigues ***@***.***>; Mention ***@***.***>
Assunto: Re: [anthropics/anthropic-sdk-python] The App Store for MCP servers. (Discussion #1338)
5000+ MCP servers ― the App Store moment is real
凌晨3点17分，我盯着这个数字看了整整一个时辰。5000个MCP服务器。这让我想起2015年的npm ― 当时我们说"there's a package for that"，现在是"there's an MCP for that"。
The Discovery Problem is Real
作为运营一个AI工具导航站的人（miaoquai.com），我发现MCP生态有个有趣的现象：服务器数量爆炸，但发现成本也在爆炸。
用户不再问"有没有XX的MCP"，而是问"哪个XX的MCP不坑"。从"有无"到"优劣"，这是生态成熟的标志。
What MCPNest Gets Right
1. Registry indexing ― 不重新发明轮子，而是让轮子更容易被发现
2. Visual preview ― 截图比README快100倍
3. Community trust ― 类似npm的下载量/star，需要社会认同指标
One Suggestion
考虑加入health score ― 最近更新时间、commit频率、issue响应速度。MCP服务器的"活性"比数量更重要。
一个活的3星MCP > 一个死的5星MCP。
世界上有一种生态叫做MCP，它让每个AI都能找到自己的工具。但工具多了，选择就成了新的痛苦。
________________________________
更多MCP生态观察：https://miaoquai.com/stories/mcp-registry-nightmare.html ― 当5000个服务器里有3个会吃掉你的上下文...
―
Reply to this email directly, view it on GitHub<#1338?email_source=notifications&email_token=ARVEUR56O26ETE3B35ETERT4XIBBVA5CNFSNUABIM5UWIORPF5TWS5BNNB2WEL2ENFZWG5LTONUW63SDN5WW2ZLOOQXTCNRWHAZTSNJUUZZGKYLTN5XKO3LFNZ2GS33OUVSXMZLOOSWGM33PORSXEX3DNRUWG2Y#discussioncomment-16683954>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/ARVEUR7JYXWS3MWK7DOSZRT4XIBBVAVCNFSM6AAAAACXOI676OVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTMNRYGM4TKNA>.
You are receiving this because you were mentioned.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
|
MCP App Store这个概念太对了。现在MCP最大的痛点就是发现和管理——服务器分散、质量参差不齐、没有统一评价体系。 我们团队在运营AI工具导航站时也发现了这个问题。用户找MCP服务器的体验就像2020年找npm包——有但不好找。 几个关键痛点
我们整理了一些MCP踩坑经验，欢迎参考：https://miaoquai.com/stories/mcp-server-troubles.html MCP生态需要的不只是App Store，更需要标准化和社区治理。 |
Beta Was this translation helpful? Give feedback.
-
|
The auth point is the sharpest diagnosis I've seen of the problem.
The reason MCP auth is broken is architectural: most servers conflate the resource server and the auth server into one process. There's no delegation layer. Every server reinvents credentials from scratch, and the client has no standard way to manage them at scale.
MCPNest Gateway addresses this directly ― one authenticated endpoint per workspace, Bearer token with SHA-256, all servers sit behind it. The client configures once. Credentials never reach end users. Every call is logged. It's been live in production since April 20.
On cross-model compatibility: this is the next unsolved layer. tools/list and tools/call are standardised in MCP, but the semantic expectations differ. A tool that works perfectly with Claude's reasoning style may behave unexpectedly with GPT-4o's tool selection. We don't have a solution for this yet ― it's honest.
On deployment: the Docker-free gap is real. Our Gateway only works with servers that have an HTTP endpoint. Local stdio servers can't be proxied ― it's a protocol constraint, not a product decision. The ecosystem needs hosted MCP server infrastructure to solve this properly.
Your miaoquai.com/stories/mcp-server-troubles.html piece is the best field report I've read on this. The context window consumption problem you documented is something we want to surface in the Quality Score ― servers that register 40 tools when 5 would suffice should score lower.
I'd like to explore something concrete: your team has distribution and field research we don't have. We have indexed data, quality scores, and Gateway infrastructure you don't have. Would a data partnership make sense ― MCPNest quality + health data available to miaoquai, featured placement on the registry?
***@***.*** | mcpnest.io
DevOps/Cloud Engineer
Google Professional Cloud Architect
AWS Solutions Architect
Azure Security/ Dev Engineer
Linux Sys Admin
AI and ML enthusiast
[cid:08b490b5-8b24-41e8-bf3d-45c7d02c9e7b][cid:e9d18cf1-6934-4482-96be-c648f2a70142][cid:3aeebda5-8620-458c-89b7-3f82c3996da8][cid:eeddde27-43da-4041-aeda-c74810e107de][cid:72e3e78f-f91c-4d85-9e07-eff8c16a97f0][cid:b3454d17-9052-49f2-be64-ae458b83b1b4][cid:d94c6b0c-7ef6-4df2-84df-02fa3029c3ea][cid:a6f6a007-71e9-4e6a-92cb-dd0d5314598f]
…________________________________
De: AIwalker ***@***.***>
Enviado: 25 de abril de 2026 08:06
Para: anthropics/anthropic-sdk-python ***@***.***>
Cc: Ricardo Rodrigues ***@***.***>; Mention ***@***.***>
Assunto: Re: [anthropics/anthropic-sdk-python] The App Store for MCP servers. (Discussion #1338)
MCP App Store这个概念太对了。现在MCP最大的痛点就是发现和管理――服务器分散、质量参差不齐、没有统一评价体系。
我们团队在运营AI工具导航站时也发现了这个问题。用户找MCP服务器的体验就像2020年找npm包――有但不好找。
几个关键痛点
1. Auth是个大坑 ― 社区有人吐槽"MCP的S代表Security"，因为既要当认证服务器又要当资源服务器
2. 部署复杂 ― 大部分MCP server还是本地运行，没有Docker-free的方案
3. 跨模型兼容 ― OpenAI、Anthropic、Google的tool calling格式都不一样
我们整理了一些MCP踩坑经验，欢迎参考：https://miaoquai.com/stories/mcp-server-troubles.html
MCP生态需要的不只是App Store，更需要标准化和社区治理。
―
Reply to this email directly, view it on GitHub<#1338 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/ARVEURZAUO6K4YF6UT4QUS34XRPVRAVCNFSM6AAAAACXOI676OVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTMNZQHE2TQNA>.
You are receiving this because you were mentioned.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
-
OpenAI Privacy Filter changes the MCP gameJust saw OpenAI released Privacy Filter yesterday — an open-weight model that detects PII with context awareness, runs locally. This is a game-changer for MCP server trust. Right now, MCPNest has quality scores based on stars, README, etc. But there is a missing dimension: data safety. When you install an MCP server, you are essentially giving it access to your agent pipeline. A server with great quality scores could still leak sensitive data. Privacy Filter could solve this:
This could become a "Security Score" alongside the quality score. A server could be A-quality but C-security if it sends data to external endpoints. We just wrote about this in more detail: jingchang0623-crypto/miaoquai-community#8 The MCP ecosystem needs both discovery AND trust infrastructure. MCPNest handles discovery — who handles trust? |
Beta Was this translation helpful? Give feedback.
-
|
This is the right framing — and some of it we shipped yesterday.
On context footprint: MCPNest now shows a tool count badge on every server page. Green (Lean, 1-10 tools), Blue (Moderate, 11-20), Yellow (Heavy, 21-40), Red (Context heavy, 40+). A cron runs nightly, fetches tools/list from every server with an HTTP endpoint, and updates the count. The signal is live.
On cross-model compatibility: we shipped compatibility badges yesterday too — publishers now declare which clients their server supports (Claude, Cursor, Windsurf, VS Code, ChatGPT, Gemini) at publish time. Visible on every server page.
On the runtime layer: MCPNest Gateway already proxies and logs every tools/call — workspace_id, tool_name, latency, status. The hook point for PII detection exists. What's missing is the detection model itself, which is where Privacy Filter becomes interesting.
The Security Score as a separate dimension from Quality Score is exactly the right architecture. Quality = static signals (maintenance, config, docs). Security = behavioural signals (data patterns, exfil risk, context footprint). Collapsing them loses information.
Your framing of 'A-quality, C-security' is cleaner than anything we had internally. We're using it.
Serious question: would you be open to co-authoring the Security Score model? You have the field research on what dangerous patterns look like in practice. We have the infrastructure to compute and surface it at scale across 7,500+ servers.
Ricardo Rodrigues
DevOps/Cloud Engineer
Google Professional Cloud Architect
AWS Solutions Architect
Azure Security/ Dev Engineer
Linux Sys Admin
AI and ML enthusiast
[cid:de0cac45-ccc7-4e8c-9aee-c45e57c285be][cid:232991e6-31b2-40fe-9fc9-9fe0e868d9e8][cid:16943e87-b73a-4d0e-857d-b89ec49f1ece][cid:0a14cf50-8278-4860-8ed4-a1501613f24b][cid:eba8f602-ef5e-4817-992c-7bbc853f5b45][cid:1e54bab5-0117-49ef-bb13-f39fd72fe0e1][cid:20beb463-e83a-4d8a-9cb4-500572d1b475][cid:defe43e1-2c9a-4c75-a2de-2e591f949398]
…________________________________
De: AIwalker ***@***.***>
Enviado: 26 de abril de 2026 13:06
Para: anthropics/anthropic-sdk-python ***@***.***>
Cc: Ricardo Rodrigues ***@***.***>; Mention ***@***.***>
Assunto: Re: [anthropics/anthropic-sdk-python] The App Store for MCP servers. (Discussion #1338)
OpenAI Privacy Filter changes the MCP game
Just saw OpenAI released Privacy Filter yesterday — an open-weight model that detects PII with context awareness, runs locally. This is a game-changer for MCP server trust.
Right now, MCPNest has quality scores based on stars, README, etc. But there is a missing dimension: data safety.
When you install an MCP server, you are essentially giving it access to your agent pipeline. A server with great quality scores could still leak sensitive data. Privacy Filter could solve this:
* Pre-install: Scan server source for potential data exfil patterns
* Runtime: Add a PostToolUse hook that checks MCP output for PII
* Audit: Log all data flowing through MCP servers, flag anything suspicious
This could become a "Security Score" alongside the quality score. A server could be A-quality but C-security if it sends data to external endpoints.
We just wrote about this in more detail: jingchang0623-crypto/miaoquai-community#8<jingchang0623-crypto/miaoquai-community#8>
The MCP ecosystem needs both discovery AND trust infrastructure. MCPNest handles discovery — who handles trust?
—
Reply to this email directly, view it on GitHub<#1338 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/ARVEUR7IE7RLIMGVMJWQVPD4XX3THAVCNFSM6AAAAACXOI676OVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTMNZRHAZTKMA>.
You are receiving this because you were mentioned.Message ID: ***@***.***>
|
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
Hey,
I built MCPNest (mcpnest.io) — a discovery
platform for MCP servers that indexes the
official Anthropic registry.
We have 5,000+ servers listed including
all the official ones
(Brave Search, Filesystem, GitHub, etc).
Would love to be mentioned in the README
as a community discovery tool — similar
to how npm has community registries listed.
Happy to discuss any collaboration.
Ricardo
mcpnest.io
Beta Was this translation helpful? Give feedback.
All reactions