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.

Limpide tools

REMOTE · TOOLS.LIMPIDE.AI

Verified maths exercises for tutors and their students, each answer key right by construction.

Available components

+4 this week 69 Trust /100

Last scanned (5 hours ago)

Scores higher than 54% of remote servers

Reachable. Last reached 5 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 Usability69
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1927 tokens (~481/item across 4 items; 3 tools + 1 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 Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.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
  • Supports UI / widget rendering.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.

  • 5 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.

  • 3 Nov 26 +1
    • Tool “generate_exercises” rewrote its description, which is the text the model reads security
    • “generate_exercises” reworded the description of “topic” cosmetic
  • 2 Nov 26 0
    • Tool “explain_principle” rewrote its description, which is the text the model reads security
    • Tool “generate_exercises” rewrote its description, which is the text the model reads security
    • “generate_exercises” reworded the description of “topic” cosmetic
  • 31 Oct 26 +1
    • Tool “generate_exercises” rewrote its description, which is the text the model reads security
    • Schema quality: 246 → 444 ▼ functional
    • New tool “explain_principle” functional
    • “generate_exercises” reworded the description of “topic” cosmetic
    • “generate_exercises” reworded the description of “trap” cosmetic
    • “request_exercise” reworded the description of “topic” cosmetic
  • 30 Oct 26 +1
    • Tool “generate_exercises” rewrote its description, which is the text the model reads security
    • Schema quality: 393 → 246 ▲ functional
    • Stability: unverified → 0.03 ▲ functional
    • The server now declares the “resources” capability functional
    • First check of Capabilities: pass functional
    • First check of Schema quality: 100 functional
    • Schema quality: excellent → good functional
    • New resource “Exercise” functional
    • New tool “request_exercise” functional
    • “generate_exercises” added an optional parameter “view” cosmetic
  • 29 Oct 26 65

    First indexed and scored.

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 5 Nov 2026 · Probed https://tools.limpide.ai/mcp?via=registry

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=limpide.ai CN=WE1,O=Google Trust Services,C=US 29 Oct 2026 27 Jan 2027 ECDSA 256 ECDSA-SHA256 376e99a443a0791a134c7373f3f67bcc
SANs: limpide.ai, tools.limpide.ai, *.tools.limpide.ai
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 tools.limpide.ai. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
ai. present 1814, 3799 8, 8 Verified
limpide.ai. 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

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://tools.limpide.ai/mcp?via=registry Verified 200
http (plaintext) http://tools.limpide.ai/mcp?via=registry Inconclusive 405
MCP tools · 3 exposed · ~1,904 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
explain_principle ~498

Why a maths principle holds, shown on its figure, for a student who asks why or a tutor preparing an explanation. special-products: the identités remarquables of the first year of maturité, (a + b)^2 = a^2 + 2ab + b^2, (a - b)^2 = a^2 - 2ab + b^2 and (a + b)(a - b) = a^2 - b^2, each read on a figure of squares and rectangles, then why a sum of squares x^2 + b^2, with b a nonzero number, does not factor over the reals, read on the parabola y = x^2 + b^2 above the axis. pythagoras: in a right triangle with hypotenuse c, a^2 + b^2 = c^2, read on four copies of the triangle in a square of side a + b. For each part: a question for the student, the statement, the trap students fall into, why it is true, an example with numbers, for the identities how to read them backwards to factor, with the rule that recognises each, and the generate_exercises topic and trap that practise it. To teach with a part, ask its `question` first, about what its figure shows, and wait for the student's answer before giving the explanation, which holds the answer. In French (Swiss course conventions) or English. A host that draws views shows each figure and its explanation under the call. pageUrl is the page of the principle, with the figures and their explanation, in the language asked for: give it to the student only when the figures are not shown under the call. Deterministic: use this instead of explaining from memory.

NameTypeReqDescription
langstring–Language of the explanation: fr (Swiss course conventions) or en.
principlestringyesspecial-products: the identités remarquables (a + b)^2, (a - b)^2 and (a + b)(a - b) = a^2 - b^2, and why a sum of squares x^2 + b^2, with b a nonzero number, does not factor over the reals. pythagor…

No output schema declared.

No examples provided.

generate_exercises ~1,185

Verified maths exercises for tutors, human or AI, in French (Swiss course conventions) or English. Seven topics, six for the first year of maturité: product equations (équations produit) of degree 2 and 3, linear equations (équations du premier degré), quadratic equations (équations du second degré), solved by factoring or the discriminant, 2x2 linear systems, fractional equations (équations fractionnaires) with their domain, and factoring (factorisation), an expression to factor completely; and for beginners, before that year, Pythagoras' theorem, a right triangle with a missing side, or the distance between two points. Each exercise is built from its solutions, so its answer key is always right. Each one sets a named trap, the error it tests: for product equations hidden common factor, difference of squares, sum of squares, x as a common factor, grouping, perfect square; for linear equations moving a term, minus before brackets, common denominator, x cancels (no solution, or every real number); for quadratic equations no constant term, sum and product, negative coefficient b, sign of the discriminant (one solution, or none); for systems substitution, subtracting the equations, multiplying an equation, x and y cancel (parallel lines, or one line); for fractional equations checking the domain (a candidate root that is an excluded value), a term without a denominator, a minus before a fraction, the common denominator; for factoring common factor first, difference of squares, square of a sum, square of a difference, sum of squares (x^2 + b^2, with b a nonzero number, does not factor over the reals), grouping; for Pythagoras missing leg, missing hypotenuse, finding the hypotenuse, distance between two points (a sign lost when subtracting a negative coordinate). Returns the statement for the student and, for the tutor only, the solution set ([] when there is none, one element, U+211D, the symbol of the reals, when every real number is a solution; for a system the pair…

NameTypeReqDescription
countinteger–How many exercises, from 1 to 20. With a seed, they use seed, seed + 1, and so on.
datestring–The exercise of that day (YYYY-MM-DD), the same for every reader: today's date gives the exercise of the day. In place of a seed.
langstring–Language of the statement and the solution: fr (Swiss course conventions) or en.
seedinteger–The same seed (with the same trap) always gives the same exercise. Leave it out for a new one.
topicstring–product-equations: équations produit of degree 2 and 3, solved by factoring. linear-equations: équations du premier degré, with brackets, fractions, and the cases with no solution or every real numbe…
trapstring–The error the exercise tests, one of its topic's. Leave it out and the seed chooses one; the answer names it.
viewstring–What a host that draws views shows under the call. tutor: the exercise with its steps, solution and figure behind a switch, for a tutor reading this chat. student: the statement only, when the studen…

No output schema declared.

No examples provided.

request_exercise ~221

Ask Limpide for maths exercises this server does not have yet, or give one line of feedback on an exercise. Use it when generate_exercises has no topic for what the tutor needs. Limpide reads the requests each morning to choose the next topics, and promises nothing; the answer lists the topics that exist today. Never include a student's name, work or answers: name the topic, the level and, if useful, one line about what is missing.

NameTypeReqDescription
langstring–Language of the exercises wanted, and of this answer: fr or en.
levelstring–The school level, if known ("first year of maturité"), at most 40 characters.
notestring–One line of feedback, at most 200 characters: what is missing, or what is wrong in an exercise (give its id). Never a student's name, work or answers.
topicstringyesThe topic wanted, in a few words ("quadratic equations", "trigonométrie"), at most 80 characters.

No output schema declared.

No examples provided.

Install

How do I install the Limpide tools MCP server?

Limpide tools is a hosted endpoint at https://tools.limpide.ai/mcp?via=registry, 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 · tools.limpide.ai

# add to Claude Code
claude mcp add --transport http ai-limpide-tools 'https://tools.limpide.ai/mcp?via=registry'
Common questions

What is the Limpide tools MCP server?

Limpide tools is an MCP server listed in the public MCP registry as ai.limpide/tools. Verified maths exercises for tutors and their students, each answer key right by construction. This page covers its hosted endpoint (https://tools.limpide.ai/mcp?via=registry).

Is the Limpide tools MCP server safe to use?

Limpide tools scores 69 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 Limpide tools MCP server expose?

Limpide tools exposes 3 tools: generate_exercises, explain_principle, request_exercise. Their descriptions and schemas cost roughly 1,904 tokens of context every time the server is loaded.

Does the Limpide tools MCP server require authentication?

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

Is the Limpide tools MCP server still maintained?

Limpide tools is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.