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_reshape ~48

Give a new shape to an array without changing its data.

NameTypeReqDescription
arrayarrayyesThe input array to reshape.
newshapeyesThe new shape (int or list of ints).

No output schema declared.

No examples provided.

np_shape ~25

Return the shape of an array.

NameTypeReqDescription
arrayarrayyesThe input array.

No output schema declared.

No examples provided.

np_shuffle ~30

Modify a sequence in-place by shuffling its contents.

NameTypeReqDescription
arrayarrayyesThe array to shuffle.

No output schema declared.

No examples provided.

np_sin ~30

Trigonometric sine, element-wise.

NameTypeReqDescription
arrayarrayyesThe input array (in radians).

No output schema declared.

No examples provided.

np_sinh ~27

Hyperbolic sine, element-wise.

NameTypeReqDescription
arrayarrayyesThe input array.

No output schema declared.

No examples provided.

np_size ~28

Return the total number of elements in an array.

NameTypeReqDescription
arrayarrayyesThe input array.
NameTypeReqDescription
resultintegeryes

No examples provided.

np_solve ~46

Solve a linear matrix equation, or system of linear equations.

NameTypeReqDescription
aarrayyesCoefficient matrix.
barrayyesOrdinate or "dependent variable" values.

No output schema declared.

No examples provided.

np_split ~73

Split an array into multiple sub-arrays.

NameTypeReqDescription
arrayarrayyesThe array to split.
axisintegerThe axis along which to split (default: 0).
indices_or_sectionsyesIf an int, the number of equal sections. If a list, the indices at which to split.

No output schema declared.

No examples provided.

np_sqrt ~31

Return the non-negative square root of an array element-wise.

NameTypeReqDescription
arrayarrayyesThe input array.

No output schema declared.

No examples provided.

np_squeeze ~49

Remove single-dimensional entries from the shape of an array.

NameTypeReqDescription
arrayarrayyesThe input array.
axisSelects a subset of the length-1 dimensions (default: all).

No output schema declared.

No examples provided.

np_std ~65

Compute the standard deviation along the specified axis.

NameTypeReqDescription
arrayarrayyesThe input array.
axisAxis along which to compute std (default: None, std of all).
ddofintegerDelta degrees of freedom for normalization (default: 0).
NameTypeReqDescription
resultyes

No examples provided.

np_subtract ~36

Element-wise subtraction of two arrays.

NameTypeReqDescription
aarrayyesFirst input array.
barrayyesSecond input array.

No output schema declared.

No examples provided.

np_sum ~63

Sum of array elements over given axis(es).

NameTypeReqDescription
arrayarrayyesThe input array.
axisAxis along which to sum (default: None, sums all).
dtypestringThe type of the returned array (default: "float64").
NameTypeReqDescription
resultyes

No examples provided.

np_svd ~43

Singular Value Decomposition.

NameTypeReqDescription
arrayarrayyesThe input array.
full_matricesbooleanWhether to compute full SVD (default: False).

Structured output declared, but exposes no named fields.

No examples provided.

np_tan ~30

Trigonometric tangent, element-wise.

NameTypeReqDescription
arrayarrayyesThe input array (in radians).

No output schema declared.

No examples provided.

np_tanh ~27

Hyperbolic tangent, element-wise.

NameTypeReqDescription
arrayarrayyesThe input array.

No output schema declared.

No examples provided.

np_tile ~46

Construct an array by repeating the input array the given number of times.

NameTypeReqDescription
arrayarrayyesThe input array to tile.
repsyesThe number of repetitions along each axis.

No output schema declared.

No examples provided.

np_trace ~55

Return the sum along the main diagonal of the array.

NameTypeReqDescription
arrayarrayyesThe input array (must be at least 2D).
offsetintegerThe diagonal offset (default: 0, main diagonal).
NameTypeReqDescription
resultnumberyes

No examples provided.

np_transpose ~47

Reverse or permute the axes of an array.

NameTypeReqDescription
arrayarrayyesThe input array.
axesBy default, reverse the axes. Otherwise, permute the axes.

No output schema declared.

No examples provided.

np_var ~64

Compute the variance along the specified axis.

NameTypeReqDescription
arrayarrayyesThe input array.
axisAxis along which to compute variance (default: None, variance of all).
ddofintegerDelta degrees of freedom for normalization (default: 0).
NameTypeReqDescription
resultyes

No examples provided.

np_zeros ~55

Create an array of zeros.

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.

npastype ~39

Copy of the array, cast to a specified type.

NameTypeReqDescription
arrayarrayyesThe input array.
dtypestringyesThe target dtype.

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.