Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Knowra

REMOTE · MCP.KNOWRA.APP

Search arXiv papers and read Scout reports with methods, evidence and verification points.

Available components

+3 this week 73 Trust /100

Last scanned (21 hours ago)

Scores higher than 60% of remote servers

Unreachable for 1 day in a row. Last reached 3 Nov 2026.

Category Education and Research

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability63
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 658 tokens (~219/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management33
  • Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage94
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 80% of tool parameters carry a description.Partial
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 4 Nov 26 0
    • Endpoint reachability: reachable → unreachable ▼ security
    • HTTPS: pass → unverified ▼ security
    • Stability: 0.30 → unverified ▼ security
    • HSTS header: fail → unverified ▼ security
    • Authorization: partial → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • TLS certificate: pass → unverified ▼ security
    • Transport: pass → fail ▼ security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Endpoint reachability: unreachable → reachable ▲ functional
    • First check of Schema quality: unverified functional
    • Server version: 0.8.15 → 0.8.16 functional
  • 3 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

  • 1 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

  • 31 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Server version: 0.8.14 → 0.8.15 functional
  • 30 Oct 26 +1
    • Server version: 0.8.13 → 0.8.14 functional
    • Server version: 0.8.12 → 0.8.13 functional
  • 29 Oct 26 0
    • Server version: 0.8.11 → 0.8.12 functional
  • 28 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 27 Oct 26 0
    • Server version: 0.8.10 → 0.8.11 functional
    • Server version: 0.8.9 → 0.8.10 functional
    • Server version: 0.8.8 → 0.8.9 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 4 Nov 2026 · Probed https://mcp.knowra.app/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=knowra.app CN=WE1,O=Google Trust Services,C=US 4 Oct 2026 2 Jan 2027 ECDSA 256 ECDSA-SHA256 8806e955897cfe121389f5c68f48bb60
SANs: knowra.app, *.knowra.app
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.knowra.app. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
app. present 23684 8 Verified
knowra.app. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
x-content-type-options nosniff

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.knowra.app/mcp Verified 200
http (plaintext) http://mcp.knowra.app/mcp Inconclusive 406
MCP tools · 3 exposed · ~472 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
get_scout ~145

Read 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 findings, or understand the context of a claim beyond the abstract. Search results mark supported papers with scout_available=true. Returns text including figure captions and descriptions. If needed, consult the original paper through source_url for further verification. Independent papers can be requested concurrently; up to five concurrent requests are recommended per batch. For a timeout, wait as indicated and retry the same paper.

NameTypeReqDescription
paper_idstringyesPaper identifier from search results; scout_available indicates Scout availability.
NameTypeReqDescription
paper_idstringyes–
scoutstringyesPaper-based Scout analysis with evidence, verification points and figure descriptions.
source_urlstringyes–

No examples provided.

get_usage ~40

Check Scout quota, usage, remaining allowance and reset time, along with plan and entitlement details. Entitlement expiry and quota reset time describe different events.

Input schema present but exposes no named parameters.

NameTypeReqDescription
billing_owner–––
entitlement_expires_at–––
entitlement_sourcestring––
hard_limitbooleanyes–
limitintegeryes–
plan_tierstringyes–
remainingintegeryes–
resets_atstringyes–
subscription_expiredbooleanyes–
usedintegeryes–
user_idstringyes–

No examples provided.

search_papers ~287

Discover 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 query each as useful. Independent queries can run concurrently; 5-10 concurrent requests are recommended for larger batches. Results can complement findings from other research tools and sources for broader coverage. scout_available indicates whether deeper paper-based analysis can be requested with get_scout; choose further reading according to the evidence needed. Use from/to as YYYY-MM-DD UTC dates with both days included. Provide both or neither; each dated query covers at most one calendar month, with dates available from 2025-08-01 onward. Omit both for all indexed dates. For timeouts, wait at least retry_after_seconds when supplied before retrying.

NameTypeReqDescription
from––First included UTC date, YYYY-MM-DD. The database supports 2025-08-01 onward. Provide both from and to, or omit both to search all supported content.
limitinteger––
querystringyesPrefer English natural-language research topics or questions; keep important entities and technical phrases.
to––Last included UTC date, YYYY-MM-DD; the entire day is included. Provide both from and to. At most one calendar month after from; same-day queries valid.
NameTypeReqDescription
papersarrayyes–
query_hint–––
returnedintegeryes–

No examples provided.

Install

How do I install the Knowra MCP server?

Knowra is a hosted endpoint at https://mcp.knowra.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · mcp.knowra.app

# add to Claude Code
claude mcp add --transport http app-knowra-knowra 'https://mcp.knowra.app/mcp'
Common questions

What is the Knowra MCP server?

Knowra is an MCP server listed in the public MCP registry as app.knowra/knowra. Search arXiv papers and read Scout reports with methods, evidence and verification points. This page covers its hosted endpoint (https://mcp.knowra.app/mcp).

Is the Knowra MCP server safe to use?

Knowra scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Knowra MCP server expose?

Knowra exposes 3 tools: search_papers, get_scout, get_usage. Their descriptions and schemas cost roughly 472 tokens of context every time the server is loaded.

Does the Knowra MCP server require authentication?

No. We connected to Knowra without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Knowra MCP server still maintained?

Knowra is still listed in the MCP registry, though our most recent checks did not reach this channel. We last reached this channel on 3 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.