
Knowra MCP server
Which MCP servers are Knowra's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-29
- Registry nameapp.knowra/knowraverified in the MCP registry
The registry name sits under knowra.app. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-29
- Tools3
- Server calls itselfKnowra
- Server version0.8.11
- Protocol version2025-06-18
On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 276 ms.
- Its tools do every use case we checked: Read structured summaries of authors' claims and evidence; Search arXiv papers from an AI assistant via MCP.
- Checked on 6 of the 7 days it takes to judge reliability.
Once connected
- For "Read structured summaries of authors' claims and evidence", the likely first call is get_scout.
- For "Search arXiv papers from an AI assistant via MCP", the likely first call is search_papers.
- Parameters are untyped or undescribed in 1 of 3 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
- What an agent can do with it2 of 2 use cases
- Answeredmeasuring6 of the 7 daily checks it takes to print a share
- Median first answer293 ms
- Space in an agent's context≈ 824 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsA · 94 of 100
- Typed results3 of 3 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 1 of 3
What an agent can do with it
- not sure · Scan a daily arXiv feed and save relevant papers
- can do · Read structured summaries of authors' claims and evidence
- can do · Search arXiv papers from an AI assistant via MCP
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
search_papersDiscover indexed arXiv papers using titles, authors and abstracts to assess relevance. Prefer an English research topic or question, preserving important entities and phrases. For broad questions, consider distinct research dimensions and…
get_scoutRead a structured paper-based analysis of key signals, methodology, evidence, experimental conditions and verification points, with author-stated limitations where available. Use it when these details help assess a candidate, compare…
get_usageCheck Scout quota, usage, remaining allowance and reset time, along with plan and entitlement details. Entitlement expiry and quota reset time describe different events.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"knowra": {
"type": "http",
"url": "https://mcp.knowra.app/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http knowra https://mcp.knowra.app/mcpclaude.ai, ChatGPT and other clients: add https://mcp.knowra.app/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.