MCP.Market

Parigp MCP server

by daedalus·io.github.daedalus/mcp-parigp·v0.1.0·1 stars
No reviews yet

MCP server exposing cypari2 (PARI/GP) number theory library

B82/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
New

1 stars12 downloads/wk

Reviews

Write one

Nobody has reviewed Parigp yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Parigp tools (100, 4 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • Catalan

    Get Catalan's constant.

  • Col

    Convert to a column vector.

  • I
  • Listwrite action

    Create an empty list or convert to a list.

  • Mat

    Convert to a matrix.

  • Modwrite action

    Create a modular number or polynomial.

  • Pol

    Convert to a polynomial.

  • Polrev

    Convert to a polynomial (reverse order).

  • Ser

    Convert to a power series.

  • Set

    Convert to a set.

  • Vec

    Convert to a row vector.

  • abs

    Compute absolute value.

  • allocatemem

    Change the PARI stack size.

  • bezout

    Compute the Bezout identity: gcd(a,b) = a*u + b*v.

  • binomial

    Compute the binomial coefficient C(n,k).

  • bnfinit

    Initialize a number field with Buchmann's algorithm.

  • bnrinit

    Initialize a ray number field (class field).

  • centerlift

    Lift a modular object with centered representatives.

  • complex
  • cos

    Compute cosine.

  • deriv

    Compute the derivative of a polynomial.

  • disc

    Compute the discriminant of a polynomial.

  • elladd

    Add two points on an elliptic curve.

  • ellap

    Compute the trace of Frobenius for an elliptic curve at prime p.

  • elleta

    Compute the eta-quotients for an elliptic curve.

  • ellglobalred

    Compute the global reduction type of an elliptic curve.

  • ellheight

    Compute the canonical height of a point on an elliptic curve.

  • ellinit

    Initialize an elliptic curve.

  • ellj

    Compute the j-invariant of an elliptic curve.

  • elllocalred

    Compute the local reduction type at prime p.

  • elllog

    Compute the discrete logarithm of a point on an elliptic curve.

  • ellmul

    Multiply a point on an elliptic curve by an integer.

  • ellorder

    Compute the order of a point on an elliptic curve.

  • elltors

    Compute the torsion subgroup of an elliptic curve.

  • ellwp

    Compute the Weierstrass p-function.

  • ellzeta

    Compute the Weierstrass zeta function.

  • euler

    Get Euler's constant.

  • eval_expression

    Evaluate a PARI/GP expression string.

  • exp

    Compute exponential.

  • factor

    Factor an integer.

  • factorial

    Compute the factorial n!.

  • factorpadic

    Factor a polynomial over the p-adic numbers.

  • fibonacci

    Compute the nth Fibonacci number.

  • gcd

    Compute the greatest common divisor of two integers.

  • get_pari_version

    Get the PARI/GP version string.

  • get_real_precision

    Get the current PARI default real precision in decimal digits.

  • get_real_precision_bits

    Get the current PARI default real precision in bits.

  • getrand

    Get PARI's current random number seed.

  • hess

    Compute the Hessenberg form of a matrix.

  • idealadd

    Add two ideals in a number field.

  • idealfactor

    Factor an ideal in a number field.

  • idealmul

    Multiply two ideals in a number field.

  • idealpow

    Compute a power of an ideal.

  • integ

    Compute the integral of a polynomial.

  • isprime

    Test if an integer is prime.

  • jacobi

    Compute the Jacobi symbol (a/n).

  • lcm

    Compute the least common multiple of two integers.

  • legendre

    Compute the Legendre symbol (a/p).

  • lift

    Lift a modular object (remove Mod wrapper).

  • log

    Compute natural logarithm.

  • lucas

    Compute the nth Lucas number.

  • matcharpoly

    Compute the characteristic polynomial of a matrix.

  • matdet

    Compute the determinant of a matrix.

  • mateigen

    Compute the eigenvalues of a matrix.

  • matidwrite action

    Create an n x n identity matrix.

  • matimage

    Compute the image of a matrix.

  • matinv

    Compute the inverse of a matrix.

  • matker

    Compute the kernel of a matrix.

  • matrank

    Compute the rank of a matrix.

  • matzerowrite action

    Create a zero matrix.

  • moebius

    Compute the Möbius function mu(n).

  • nfinit

    Initialize a number field defined by a polynomial.

  • norm

    Compute the norm of a polynomial/algebraic number.

  • one

    Get the integer 1.

  • phi

    Compute Euler's totient function phi(n).

  • pi

    Get the value of pi.

  • polchebyshev

    Compute the nth Chebyshev polynomial of the first kind.

  • polcyclo

    Compute the nth cyclotomic polynomial.

  • polhermite

    Compute the nth Hermite polynomial (probabilists' version).

  • pollegendre

    Compute the nth Legendre polynomial.

  • polroots

    Compute the complex roots of a polynomial.

  • polrootsmod

    Compute the roots of a polynomial modulo p.

  • polrootspadic

    Compute the p-adic roots of a polynomial.

  • prime

    Return the nth prime (1-indexed).

  • primes

    Return prime numbers.

  • resultant

    Compute the resultant of two polynomials.

  • set_real_precision

    Set the PARI default real precision in decimal digits.

  • set_real_precision_bits

    Set the PARI default real precision in bits.

  • setrand

    Set PARI's random number seed.

  • sigma

    Compute the sum of k-th powers of divisors of n.

  • sin

    Compute sine.

  • sqrt

    Compute square root.

  • stacksize

    Get the current PARI stack size in bytes.

  • stacksizemax

    Get the maximum PARI stack size in bytes.

  • subst

    Substitute a variable in a polynomial.

  • tan

    Compute tangent.

  • trace

    Compute the trace of a polynomial/algebraic number.

  • zero

    Get the integer 0.

  • znorder

    Compute the multiplicative order of x modulo n.

  • znstar

    Compute the structure of (Z/nZ)*.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan3 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 159 days ago8/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Parigp compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
82/100
higher than 63% of 48,273 servers
Tools
100
the typical server has 7
Tools that change things
4%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
1
more than 65% of 28,534 servers
Downloads a week
12
more than 3% of 11,915 servers with a package

What its tools let an agent do: 91 read · 8 change · 1 run or deploy

Install Parigp in Claude Code, Cursor or VS Code

claude mcp add mcp-parigp -- uvx mcp-parigp
Add to Cursor

What the publisher says

From the Parigp repository's README, as published. We do not edit it. Read it on GitHub

mcp-parigp

MCP server exposing cypari2 (PARI/GP) number theory library

mcp-name: io.github.daedalus/mcp-parigp

Install

pip install mcp-parigp

Usage

As MCP Server

Run directly:

mcp-parigp

Or use with an MCP client by configuring in your settings:

{
  "mcpServers": {
    "mcp-parigp": {
      "command": "mcp-parigp"
    }
  }
}

In Python

from mcp_parigp import eval_expression, factor, isprime

# Evaluate PARI/GP expressions
result = eval_expression("factor(100)")
print(result)  # [[2, 2], [5, 2]]

# Factor integers
print(factor(100))  # [[2, 2], [5, 2]]

# Test primality
print(isprime(29))  # True

API

Number Theory

  • factor(n) - Factor an integer
  • isprime(n) - Test if n is prime
  • gcd(a, b) - Greatest common divisor
  • phi(n) - Euler's totient function
  • sigma(n, k) - Sum of k-th power of divisors
  • jacobi(a, n) - Jacobi symbol
  • znorder(x, n) - Multiplicative order modulo n
  • primes(n) - First n primes
  • nextprime(n) - Next prime after n

Polynomials

  • polroots(pol) - Find roots of polynomial
  • polcyclo(n) - n-th cyclotomic polynomial
  • deriv(pol) - Derivative of polynomial
  • subst(pol, v, expr) - Substitute in polynomial

Number Fields

  • nfinit(pol) - Initialize number field
  • bnfinit(pol) - Initialize with Buchmann's algorithm
  • idealadd(nf, a, b) - Add ideals
  • idealmul(nf, a, b) - Multiply ideals

Elliptic Curves

  • ellinit(eq) - Initialize elliptic curve
  • ellap(E, p) - Trace of Frobenius at p
  • elltors(E) - Torsion subgroup
  • ellheight(E, P) - Canonical height

Matrices

  • matid(n) - n×n identity matrix
  • matdet(m) - Matrix determinant
  • matinv(m) - Matrix inverse
  • matrank(m) - Matrix rank

Elementary Functions

  • sin, cos, tan, asin, acos, atan
  • sinh, cosh, tanh, asinh, acosh, atanh
  • exp, log, sqrt, abs
  • pi(), euler(), I()

Development

git clone https://github.com/daedalus/mcp-parigp.git
cd mcp-parigp
pip install -e ".[test]"

# run tests
pytest

# format
ruff format src/ tests/

# lint
ruff check src/ tests/

# type check
mypy src/

Nothing above is checked by us. What we check is on the safety report.

Parigp: common questions

Is Parigp MCP server safe?
Mostly: it is graded B (82/100). Read the Parigp safety report
How do I install Parigp?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Parigp need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Parigp maintained?
The last commit was 195 days ago (2026-04-21). The latest release is v0.1.0.
How does Parigp compare with other MCP servers?
safety score 82/100 (higher than 63% of 48,273 servers); tools 100 (the typical server has 7); tools that change things 4% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

More from daedalus →