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.

io.github.daedalus/mcp-numpy

PYPI · MCP-NUMPY · SCANNED SEP 20

An MCP server that exposes NumPy functionality

Available components

−15 this week 55 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security50
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 1 of 16 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability80
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 3263 tokens (~45/item across 72 items; 72 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: two runs of the same published version returned different tool surfaces, so we cannot tell a change in the package from a difference in our own sandbox run.Unverified
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 99% of tool parameters carry a description.Partial
  • Structured output schemas are declared (28% of tools); any adoption earns full credit.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "np_squeeze" implies "remove" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 72 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

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

Install

How do I install the io.github.daedalus/mcp-numpy server?

io.github.daedalus/mcp-numpy runs locally as a PyPI package, launched with uvx mcp-numpy. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · mcp-numpy

# add to Claude Code
claude mcp add daedalus-mcp-numpy -- uvx mcp-numpy
// .cursor/mcp.json
{
  "mcpServers": {
    "daedalus-mcp-numpy": {
      "command": "uvx",
      "args": [
        "mcp-numpy"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "daedalus-mcp-numpy": {
      "command": "uvx",
      "args": [
        "mcp-numpy"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add daedalus-mcp-numpy -- uvx mcp-numpy
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "daedalus-mcp-numpy": {
      "type": "local",
      "command": [
        "uvx",
        "mcp-numpy"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add daedalus-mcp-numpy --command uvx --arg mcp-numpy
# ~/.hermes/config.yaml
mcp_servers:
  daedalus-mcp-numpy:
    command: "uvx"
    args: ["mcp-numpy"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "daedalus-mcp-numpy": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "mcp-numpy"
      ]
    }
  }
}
# add to Vellum
assistant mcp add daedalus-mcp-numpy -t stdio -c uvx -a mcp-numpy
// mcp.json
{
  "mcpServers": {
    "daedalus-mcp-numpy": {
      "command": "uvx",
      "args": [
        "mcp-numpy"
      ]
    }
  }
}
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.

  • 20 Sept 26 −15
    • Malware scan: pass → unverified security
  • 19 Sept 26 +15
    • Malware scan: unverified → pass security
  • 17 Sept 26 −15
    • Malware scan: pass → unverified security
  • 15 Sept 26 +15
    • Malware scan: unverified → pass security
  • 14 Sept 26 −15
    • Malware scan: pass → unverified security
  • 12 Sept 26 +15
    • Malware scan: unverified → pass security
  • 11 Sept 26 −15
    • Malware scan: pass → unverified security
  • 9 Sept 26 −13
    • Stability: 0.90 → unverified security
    • Tool coverage: 100% → 28% 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 20 Sept 2026 · Analysed pypi/mcp-numpy@0.1.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 16 packages
Packages resolved 16
Stale 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 72 exposed · ~3,263 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
np_abs ~26

Calculate the absolute value of array elements.

NameTypeReqDescription
arrayarrayyesThe input array.

No output schema declared.

No examples provided.

np_add ~35

Element-wise addition of two arrays.

NameTypeReqDescription
aarrayyesFirst input array.
barrayyesSecond input array.

No output schema declared.

No examples provided.

np_arange ~78

Create an array with evenly spaced values within a given interval.

NameTypeReqDescription
dtypestringThe data type of the array (default: "float64").
startnumberyesStart of interval.
stepnumberSpacing between values (default: 1).
stopnumberyesEnd of interval (exclusive).

No output schema declared.

No examples provided.

np_arccos ~36

Inverse cosine, element-wise.

NameTypeReqDescription
arrayarrayyesThe input array (must be in [-1, 1]).

No output schema declared.

No examples provided.

np_arcsin ~36

Inverse sine, element-wise.

NameTypeReqDescription
arrayarrayyesThe input array (must be in [-1, 1]).

No output schema declared.

No examples provided.

np_arctan ~27

Inverse tangent, element-wise.

NameTypeReqDescription
arrayarrayyesThe input array.

No output schema declared.

No examples provided.

np_argmax ~48

Return the indices of the maximum values along an axis.

NameTypeReqDescription
arrayarrayyesThe input array.
axisAxis along which to find argmax (default: None, flattened).
NameTypeReqDescription
resultyes

No examples provided.

np_argmin ~48

Return the indices of the minimum values along an axis.

NameTypeReqDescription
arrayarrayyesThe input array.
axisAxis along which to find argmin (default: None, flattened).
NameTypeReqDescription
resultyes

No examples provided.

np_array ~73

Create a NumPy array from a list.

NameTypeReqDescription
dataarrayyesA Python list containing the array elements.
dtypestringThe data type of the array (default: "float64"). Common values: "int32", "int64", "float32", "float64", "complex128".

No output schema declared.

No examples provided.

np_concatenate ~51

Join a sequence of arrays along an existing axis.

NameTypeReqDescription
arraysarrayyesA sequence of arrays to concatenate.
axisintegerThe axis along which to concatenate (default: 0).

No output schema declared.

No examples provided.

np_corrcoef ~58

Return Pearson product-moment correlation coefficients.

NameTypeReqDescription
arrayarrayyesA 1-D or 2-D array containing multiple variables and observations.
rowvarbooleanIf True, each row represents a variable (default: True).

No output schema declared.

No examples provided.

np_correlate ~66

Cross-correlation of two 1-dimensional sequences.

NameTypeReqDescription
aarrayyesFirst input sequence.
barrayyesSecond input sequence.
modestringComputation mode (default: "full"). Options: "full", "same", "valid".

No output schema declared.

No examples provided.

np_cos ~29

Trigonometric cosine, element-wise.

NameTypeReqDescription
arrayarrayyesThe input array (in radians).

No output schema declared.

No examples provided.

np_cosh ~27

Hyperbolic cosine, element-wise.

NameTypeReqDescription
arrayarrayyesThe input array.

No output schema declared.

No examples provided.

np_cross ~36

Compute the cross product of two arrays.

NameTypeReqDescription
aarrayyesFirst input array.
barrayyesSecond input array.

No output schema declared.

No examples provided.

np_cumprod ~51

Return the cumulative product of the array along a given axis.

NameTypeReqDescription
arrayarrayyesThe input array.
axisThe axis along which to compute cumprod (default: None, flattened).

No output schema declared.

No examples provided.

np_cumsum ~50

Return the cumulative sum of the array along a given axis.

NameTypeReqDescription
arrayarrayyesThe input array.
axisThe axis along which to compute cumsum (default: None, flattened).

No output schema declared.

No examples provided.

np_det ~29

Compute the determinant of an array.

NameTypeReqDescription
arrayarrayyesThe input matrix (must be square).
NameTypeReqDescription
resultnumberyes

No examples provided.

np_diag ~61

Create a diagonal array or extract the diagonal of an array.

NameTypeReqDescription
dtypestringThe data type of the array (default: "float64").
kyesIf a list, creates diagonal array from it. If an int, extracts that diagonal.

No output schema declared.

No examples provided.

np_diff ~67

Calculate the n-th discrete difference along the given axis.

NameTypeReqDescription
arrayarrayyesThe input array.
axisintegerThe axis along which to difference (default: 0).
nintegerThe number of times values are differenced (default: 1).

No output schema declared.

No examples provided.

np_divide ~42

Element-wise division of two arrays.

NameTypeReqDescription
aarrayyesFirst input array (dividend).
barrayyesSecond input array (divisor).

No output schema declared.

No examples provided.

np_dot ~36

Compute the dot product of two arrays.

NameTypeReqDescription
aarrayyesFirst input array.
barrayyesSecond input array.
NameTypeReqDescription
resultyes

No examples provided.

np_dtype ~25

Return the dtype of an array.

NameTypeReqDescription
arrayarrayyesThe input array.
NameTypeReqDescription
resultstringyes

No examples provided.

np_eig ~32

Compute the eigenvalues and eigenvectors of a square array.

NameTypeReqDescription
arrayarrayyesThe input square matrix.

Structured output declared, but exposes no named fields.

No examples provided.

np_exp ~28

Calculate the exponential of all elements in the array.

NameTypeReqDescription
arrayarrayyesThe input array.

No output schema declared.

No examples provided.

np_eye ~47

Return a 2D identity array.

NameTypeReqDescription
dtypestringThe data type of the array (default: "float64").
m
nintegeryes

No output schema declared.

No examples provided.

np_flatten ~27

Return a flattened copy of the array.

NameTypeReqDescription
arrayarrayyesThe input array.

No output schema declared.

No examples provided.

np_full ~72

Create an array filled with a constant value.

NameTypeReqDescription
dtypestringThe data type of the array (default: "float64").
fill_valuenumberyesThe value to fill the array with.
shapeyesAn integer for 1D shape, or a list of integers for multi-dimensional.

No output schema declared.

No examples provided.

np_histogram ~63

Compute the histogram of a set of data.

NameTypeReqDescription
arrayarrayyesInput data.
binsNumber of bins or bin edges (default: 10).
rangeThe lower and upper range of the bins (default: [min, max]).

Structured output declared, but exposes no named fields.

No examples provided.

np_inv ~37

Compute the (multiplicative) inverse of a matrix.

NameTypeReqDescription
arrayarrayyesThe input matrix (must be square and invertible).

No output schema declared.

No examples provided.

np_linalg_norm ~76

Matrix or vector norm.

NameTypeReqDescription
arrayarrayyesThe input array.
ordstringThe order of the norm (default: "fro" for matrices, "2" for vectors). Common values: "fro", "nuc", "inf", "-inf", "0", "1", "2".
NameTypeReqDescription
resultnumberyes

No examples provided.

np_linspace ~77

Create an array with evenly spaced numbers over a specified interval.

NameTypeReqDescription
dtypestringThe data type of the array (default: "float64").
numintegerNumber of samples to generate (default: 50).
startnumberyesStart of interval.
stopnumberyesEnd of interval.

No output schema declared.

No examples provided.

np_log ~25

Natural logarithm, element-wise.

NameTypeReqDescription
arrayarrayyesThe input array.

No output schema declared.

No examples provided.

np_log10 ~28

Base-10 logarithm, element-wise.

NameTypeReqDescription
arrayarrayyesThe input array.

No output schema declared.

No examples provided.

np_matmul ~41

Matrix product of two arrays.

NameTypeReqDescription
aarrayyesFirst input array (2D).
barrayyesSecond input array (2D).

No output schema declared.

No examples provided.

np_max ~49

Return the maximum of an array or maximum along an axis.

NameTypeReqDescription
arrayarrayyesThe input array.
axisAxis along which to find maximum (default: None, max of all).
NameTypeReqDescription
resultyes

No examples provided.

np_mean ~46

Compute the arithmetic mean along the specified axis.

NameTypeReqDescription
arrayarrayyesThe input array.
axisAxis along which to compute mean (default: None, mean of all).
NameTypeReqDescription
resultyes

No examples provided.

np_min ~49

Return the minimum of an array or minimum along an axis.

NameTypeReqDescription
arrayarrayyesThe input array.
axisAxis along which to find minimum (default: None, min of all).
NameTypeReqDescription
resultyes

No examples provided.

np_mod ~41

Element-wise modulo of two arrays.

NameTypeReqDescription
aarrayyesFirst input array (dividend).
barrayyesSecond input array (divisor).

No output schema declared.

No examples provided.

np_multiply ~36

Element-wise multiplication of two arrays.

NameTypeReqDescription
aarrayyesFirst input array.
barrayyesSecond input array.

No output schema declared.

No examples provided.

np_ndim ~28

Return the number of dimensions of an array.

NameTypeReqDescription
arrayarrayyesThe input array.
NameTypeReqDescription
resultintegeryes

No examples provided.

np_ones ~55

Create an array of ones.

NameTypeReqDescription
dtypestringThe data type of the array (default: "float64").
shapeyesAn integer for 1D shape, or a list of integers for multi-dimensional.

No output schema declared.

No examples provided.

np_percentile ~51

Compute the q-th percentile of the array elements.

NameTypeReqDescription
arrayarrayyesThe input array.
qyesPercentile(s) to compute (0-100). Can be a float or list.
NameTypeReqDescription
resultyes

No examples provided.

np_power ~39

Element-wise exponentiation of array elements.

NameTypeReqDescription
aarrayyesThe base array.
byesThe exponent (can be array or scalar).

No output schema declared.

No examples provided.

np_quantile ~52

Compute the q-th quantile of the array elements.

NameTypeReqDescription
arrayarrayyesThe input array.
qyesQuantile(s) to compute (0-1). Can be a float or list.
NameTypeReqDescription
resultyes

No examples provided.

np_rand ~31

Random values in a given shape.

NameTypeReqDescription
shapeyesThe shape of the output (int or list of ints).

No output schema declared.

No examples provided.

np_randint ~80

Return random integers from low (inclusive) to high (exclusive).

NameTypeReqDescription
highUpper bound (exclusive). If None, low=0 and this becomes high.
lowintegeryesLowest integers to be drawn (inclusive). If high is None, this is the upper bound.
sizeOutput shape (int or tuple of ints).

No output schema declared.

No examples provided.

np_randn ~40

Return a sample (or samples) from the "standard normal" distribution.

NameTypeReqDescription
shapeyesThe shape of the output (int or list of ints).

No output schema declared.

No examples provided.

np_random_choice ~65

Generates a random sample from a given array.

NameTypeReqDescription
aarrayyes1-D array-like object from which to sample.
replacebooleanWhether sampling with replacement (default: True).
sizeOutput shape (default: None, returns single value).

No output schema declared.

No examples provided.

np_repeat ~56

Repeat elements of an array.

NameTypeReqDescription
arrayarrayyesThe input array.
axisThe axis along which to repeat values (default: flattens).
repeatsintegeryesThe number of repetitions for each element.

No output schema declared.

No examples provided.

Common questions

What is the io.github.daedalus/mcp-numpy server?

io.github.daedalus/mcp-numpy is listed in the public MCP registry as io.github.daedalus/mcp-numpy. An MCP server that exposes NumPy functionality. This page covers its PyPI package (mcp-numpy).

Is the io.github.daedalus/mcp-numpy server safe to use?

io.github.daedalus/mcp-numpy scores 55 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. 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 io.github.daedalus/mcp-numpy server expose?

io.github.daedalus/mcp-numpy exposes 72 tools: np_array, np_zeros, np_ones, np_full, np_arange, and 67 more. Their descriptions and schemas cost roughly 3,263 tokens of context every time the server is loaded.

Is the io.github.daedalus/mcp-numpy server still maintained?

io.github.daedalus/mcp-numpy is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.daedalus/mcp-numpy server under?

io.github.daedalus/mcp-numpy declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.