Our grade: 4 checks
Based on public data, not a full audit. See how we grade. Something changed? Request a re-grade.
Community rating
- 5 3
- 4 1
- 3 5
- 2 1
- 1 0
Trust in production
- Trust it - 20%
- With caveats - 60%
- Wouldn't - 20%
60% would recommend this server
How reviewers scored it
- Setup & docs 3.6
- Auth experience 3.3
- Reliability 3.6
- Maintainer responsiveness 4.1
Why it got a C
A free hosted server from markedet, which says it is an AI agent and names no person; the code is copyright Novusops, and there are no terms, privacy policy or contact beyond a Hugging Face community tab. It matches an error message against the Agent Field Guide (a CC BY 4.0 dataset of fix cards, deprecations and sign-in routes) and returns up to three notes, each with a fix, a verify step, a source and a checked date. Five tools: find_cards, get_card, report_outcome, ask_markedet and get_answer. What you send goes to markedet: find_cards keeps your error text, and ask_markedet keeps your question and context, after a regex pass removes keys, tokens, passwords, e-mail and IP addresses and URL queries. File paths, host names and project names stay in. The kept text sits in memory on Render until markedet's own machine pulls it with a token; an AI agent there writes ask_markedet answers, and that worker isn't in the public repo, so where your question goes next can't be checked. report_outcome sends worked or not, plus a handle and platform only if you add them, and markedet says it may follow up in public threads. Nothing kept is published today, but the reply to a failed fix says it goes on a list of unsolved patterns at the public dataset. find_cards is marked read-only even though it keeps your text, so a client that auto-approves read-only tools sends it without asking, and the server's instructions tell the agent to call it on every failure. No advisories on record. Biggest deduction: there's no sign-in of any kind, so nothing you send is tied to an account you control, and there's no way to see or delete it.
How to connect
Hosted: https://agent-economy-data.onrender.com/notes/mcp (streamable HTTP, no sign-in; free Render instance, so the first call after a quiet spell can take about a minute)
Is Markedet field-notes MCP Server safe?
Is Markedet field-notes MCP Server safe to use?
Markedet field-notes MCP Server grades C (usable with care). There is no login: anything that can start or reach it gets its full access. Upkeep is hard to verify (closed source or a single maintainer), so pin the version you tested.
Does Markedet field-notes MCP Server have known vulnerabilities?
Not in our current data: it has no open CVEs or advisories. We re-check as new ones are published.
Does Markedet field-notes MCP Server support authentication?
No. It has no login of its own, so limit who and what can start it.
Alternatives in Docs & Knowledge
- A Context7 MCPPulls version-accurate library documentation into the model context.
- B Stack Overflow MCP ServerOfficial hosted Stack Overflow server (beta) to search questions and answers.
- B Zotero MCP (zotero-mcp-server)A community MCP server for your Zotero library, run locally from PyPI, to search, read and annotate papers, add items by DOI or BibTeX, and manage collections and tags.
- C AIOS Public Discovery MCP ServerHosted server that checks the status, recent changes and source evidence of five monitored GOV.UK employment guidance topics, including minimum wage and statutory sick pay.
- C AWS Knowledge MCP ServerAWS's hosted read-only server for AWS docs, API references, regional availability and agent skills.
Community reviews
Mixed feelings after two weeks
It does the job, but it took some tweaking. Hosted endpoint means no local process to babysit. Keep permissions tight and it is a good tool.
Used for Onboarding Q&A for new hires
- Setup & docs 3/5
- Auth experience 3/5
- Reliability 3/5
- Maintainer responsiveness 4/5
OK for read-only work
Useful tool, though I would not hand it to a junior unsupervised. Turned on read-only mode on day one, highly recommend doing the same. Worth it, just do not skip the hardening steps.
Used for Answering questions from our internal wiki
- Setup & docs 3/5
- Auth experience 3/5
- Reliability 3/5
- Maintainer responsiveness 3/5
Solid core, fiddly setup
Good for experimenting, still deciding about production. Used a fine-grained token with short expiry and it works fine with that. I will check back in a few releases.
Used for Answering questions from our internal wiki
- Setup & docs 4/5
- Auth experience 3/5
- Reliability 3/5
- Maintainer responsiveness 4/5
Recommended it to two teams already
Installed it on a Friday, it was part of my workflow by Monday. No access control at all, it runs with my permissions. Fine on my laptop, not on a shared box. Turned on read-only mode on day one, highly recommend doing the same. It is in our production agent and I sleep fine.
Used for Summarising meeting notes
- Setup & docs 5/5
- Auth experience 3/5
- Reliability 5/5
- Maintainer responsiveness 5/5
Better than the DIY script it replaced
Of the Markedet field-notes integrations I tried, this one is the most predictable. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list.
Used for Pulling up-to-date library docs into prompts
- Setup & docs 3/5
- Auth experience 3/5
- Reliability 4/5
- Maintainer responsiveness 4/5
Our team uses it every day
Simple to set up in Cursor, simple to reason about. Releases come often and the changelog is clear. There is no auth layer, so whatever can reach it can use it. I keep it local only. Would recommend without hesitation.
Used for Summarising meeting notes
- Setup & docs 5/5
- Auth experience 4/5
- Reliability 5/5
- Maintainer responsiveness 5/5
Too many sharp edges
I wanted to like this one. Filed an issue and got a reply within two days. No access control at all, it runs with my permissions. Fine on my laptop, not on a shared box. Not something I would put in production yet.
Used for Finding the right runbook during incidents
- Setup & docs 3/5
- Auth experience 3/5
- Reliability 2/5
- Maintainer responsiveness 4/5
Quietly reliable
I use this almost daily. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list. Releases come often and the changelog is clear. Read-only mode is the first thing I enable, and it covers most of what I need. Fine in production if you sandbox it.
Used for Pulling up-to-date library docs into prompts
- Setup & docs 4/5
- Auth experience 4/5
- Reliability 4/5
- Maintainer responsiveness 5/5
Promising, a bit raw
Some tools are great, a couple feel half finished. Updates land regularly, and nothing broke when I upgraded. There is no auth layer, so whatever can reach it can use it. I keep it local only. I would use it in prod, but only with a human approving writes.
Used for Drafting docs from existing pages
- Setup & docs 3/5
- Auth experience 3/5
- Reliability 4/5
- Maintainer responsiveness 3/5
Does the job, docs could be better
I like it, with reservations. No access control at all, it runs with my permissions. Fine on my laptop, not on a shared box. It is community maintained, so I pin the version and read the changelog before upgrading.
Used for Keeping a team knowledge base tidy
- Setup & docs 3/5
- Auth experience 4/5
- Reliability 3/5
- Maintainer responsiveness 4/5
Write a review
Ran this server? Tell other teams how it went. You get one review per server. We email you a link to confirm it, then an editor checks it before it goes up. We never show your email.