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 1
- 4 7
- 3 6
- 2 3
- 1 0
Trust in production
- Trust it - 18%
- With caveats - 59%
- Wouldn't - 24%
53% would recommend this server
How reviewers scored it
- Setup & docs 3.4
- Auth experience 2.7
- Reliability 3.2
- Maintainer responsiveness 3.6
Why it got a C
An MIT-licensed Node server (four tools: help, list_models, search_prompts, optimize_prompt) that runs on your machine over stdio and calls InkRoom's hosted API for the prompt data, with shared free-use quotas. It needs no account or key, never generates images, and runs no shell commands. The optional HTTP mode listens only on 127.0.0.1 and rejects other origins. Prompts it returns were written by other people, so treat them as untrusted text. The MIT license covers this distribution only, not third-party prompts or images, or InkRoom's separate hosted Image MCP. No advisories on record. Biggest deduction: there is no auth layer at all. Also check the source: the install command runs a release archive from the inkroom-client repository, where development happens. The inkroom-prompts repo is a one-way export of that prompts-v1.0.4 release, with per-file hashes in SOURCE_MANIFEST.json. To run from source instead, clone inkroom-prompts, run npm ci --ignore-scripts, then start src/cli.mjs with node.
How to connect
// .cursor/mcp.json
{ "mcpServers": { "inkroom-prompts": { "command": "npx", "args": ["-y", "--package", "https://github.com/InkRoom-AI/inkroom-client/releases/download/prompts-v1.0.4/inkroom-prompts-1.0.4.tgz", "inkroom-prompts"] } } }
claude mcp add inkroom-prompts -- npx -y --package https://github.com/InkRoom-AI/inkroom-client/releases/download/prompts-v1.0.4/inkroom-prompts-1.0.4.tgz inkroom-prompts
// claude_desktop_config.json
{ "mcpServers": { "inkroom-prompts": { "command": "npx", "args": ["-y", "--package", "https://github.com/InkRoom-AI/inkroom-client/releases/download/prompts-v1.0.4/inkroom-prompts-1.0.4.tgz", "inkroom-prompts"] } } }
Is InkRoom Prompts MCP Server safe?
Is InkRoom Prompts MCP Server safe to use?
InkRoom Prompts MCP Server grades C (usable with care). There is no login: anything that can start or reach it gets its full access. Updates are occasional, so fixes may be slow to arrive. It runs locally over stdio, so it acts with your machine's access.
Does InkRoom Prompts 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 InkRoom Prompts MCP Server support authentication?
No. It has no login of its own, so limit who and what can start it.
Alternatives in Search & Retrieval
- A Exa MCPOfficial hosted Exa server for web search, page fetching, and multi-step research.
- A Perplexity MCP ServerOfficial Perplexity server for web search, quick answers, reasoning, and deep research through the Perplexity API.
- A Tavily MCPOfficial Tavily server for web search, page extraction, site mapping, crawling, and research.
- B Firecrawl MCP ServerOfficial Firecrawl server to search the web, scrape and crawl sites, parse documents, and interact with pages in a cloud browser.
- B LawDB MCP ServerHosted server to search German and EU legislation and German, European and international case law, and fetch full texts and single provisions with stable citations.
Community reviews
Useful, with a few rough edges
Works well enough for what I need. Issues get answered eventually. Not fast, not abandoned. I will check back in a few releases.
Used for Grounding answers with live results
- Setup & docs 2/5
- Auth experience 2/5
- Reliability 3/5
- Maintainer responsiveness 4/5
Good, but read the permissions first
Useful tool, though I would not hand it to a junior unsupervised. Nice that it supports both stdio and HTTP, I use stdio locally and HTTP for the shared agent. Keep permissions tight and it is a good tool.
Used for Competitive research
- Setup & docs 3/5
- Auth experience 4/5
- Reliability 3/5
- Maintainer responsiveness 3/5
Handy for dev, careful in prod
I like it, with reservations. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list. For anything real I would look elsewhere.
Used for Technical research while coding
- Setup & docs 3/5
- Auth experience 3/5
- Reliability 3/5
- Maintainer responsiveness 3/5
Does the job, docs could be better
Mostly reliable, with the odd timeout. There is no auth layer, so whatever can reach it can use it. I keep it local only. Fine in production if you sandbox it.
Used for Grounding answers with live results
- Setup & docs 3/5
- Auth experience 4/5
- Reliability 3/5
- Maintainer responsiveness 3/5
Too much access for my comfort
Ran into problems pretty quickly. 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 recent sources for articles
- Setup & docs 2/5
- Auth experience 2/5
- Reliability 3/5
- Maintainer responsiveness 4/5
Good defaults, good docs
Of the InkRoom Prompts integrations I tried, this one is the most predictable. There is no auth layer, so whatever can reach it can use it. I keep it local only. Updates are a bit slow, but it is stable enough that it has not mattered.
Used for Technical research while coding
- Setup & docs 4/5
- Auth experience 2/5
- Reliability 3/5
- Maintainer responsiveness 5/5
Our team uses it every day
I use this almost daily. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list. It is in our production agent and I sleep fine.
Used for Collecting references for reports
- Setup & docs 5/5
- Auth experience 4/5
- Reliability 5/5
- Maintainer responsiveness 4/5
Easy win for our agent setup
Started with it as an experiment, now it is a fixture. Issues get answered eventually. Not fast, not abandoned. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list.
Used for Research agent for market questions
- Setup & docs 3/5
- Auth experience 3/5
- Reliability 3/5
- Maintainer responsiveness 4/5
Saves me a context switch every hour
Set this up for our team after comparing a few options. There is no auth layer, so whatever can reach it can use it. I keep it local only. Worth it, just do not skip the hardening steps.
Used for Collecting references for reports
- Setup & docs 4/5
- Auth experience 2/5
- Reliability 4/5
- Maintainer responsiveness 4/5
Fine once configured properly
It does the job, but it took some tweaking. Nice that it supports both stdio and HTTP, I use stdio locally and HTTP for the shared agent. Release pace is moderate, so I pin a version and check in monthly.
Used for Research agent for market questions
- Setup & docs 3/5
- Auth experience 4/5
- Reliability 3/5
- Maintainer responsiveness 3/5
Quietly reliable
Replaced a homegrown script with InkRoom Prompts MCP Server and have not looked back. There is no auth layer, so whatever can reach it can use it. I keep it local only.
Used for Competitive research
- Setup & docs 4/5
- Auth experience 3/5
- Reliability 3/5
- Maintainer responsiveness 4/5
Surprisingly polished
Installed it on a Friday, it was part of my workflow by Monday. Nice that it supports both stdio and HTTP, I use stdio locally and HTTP for the shared agent. Updates are a bit slow, but it is stable enough that it has not mattered. Recommended, with sensible guardrails.
Used for Finding recent sources for articles
- Setup & docs 5/5
- Auth experience 2/5
- Reliability 3/5
- Maintainer responsiveness 3/5
The InkRoom Prompts integration I wanted
Clear tool names, sensible outputs, very few surprises. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list.
Used for Grounding answers with live results
- Setup & docs 4/5
- Auth experience 2/5
- Reliability 4/5
- Maintainer responsiveness 4/5
OK for read-only work
Some tools are great, a couple feel half finished. Updates are a bit slow, but it is stable enough that it has not mattered. No access control at all, it runs with my permissions. Fine on my laptop, not on a shared box. I would use it in prod, but only with a human approving writes.
Used for Fact-checking drafts
- Setup & docs 4/5
- Auth experience 2/5
- Reliability 2/5
- Maintainer responsiveness 3/5
Too many sharp edges
Gave it a fair shot over two weeks. Release pace is moderate, so I pin a version and check in monthly. No access control at all, it runs with my permissions. Fine on my laptop, not on a shared box. Recommended, with sensible guardrails.
Used for Fact-checking drafts
- Setup & docs 3/5
- Auth experience 2/5
- Reliability 3/5
- Maintainer responsiveness 2/5
Earned a permanent spot in my config
Tried it on a side project first, then rolled it out at work. There is no auth layer, so whatever can reach it can use it. I keep it local only. Nice that it supports both stdio and HTTP, I use stdio locally and HTTP for the shared agent. Happy to run it in production.
Used for Fact-checking drafts
- Setup & docs 5/5
- Auth experience 3/5
- Reliability 4/5
- Maintainer responsiveness 5/5
Needs more maintenance love
It works in a demo, but things got shaky under real use. Nothing stops a misbehaving agent from using every tool it exposes, so I trimmed the tool list.
Used for Technical research while coding
- Setup & docs 1/5
- Auth experience 2/5
- Reliability 2/5
- 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.