mathmethods-mcp 0.1.0__tar.gz → 0.2.0__tar.gz

{mathmethods_mcp-0.1.0 → mathmethods_mcp-0.2.0}/PKG-INFO

@@ -1,9 +1,14 @@
 Metadata-Version: 2.4
 Name: mathmethods-mcp
-Version: 0.1.0
+Version: 0.2.0
 Summary: MCP server exposing numerical-methods tools: bisection, Simpson 1/3, Runge-Kutta 4, Lagrange interpolation
 License-Expression: MIT
 Project-URL: Repository, https://github.com/agmonetti/mathmethods-mcp
+Keywords: mcp,model-context-protocol,numerical-methods,mathematics,calculus,scientific-computing
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Mathematics
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
@@ -14,14 +19,19 @@ Requires-Dist: scipy>=1.11.0
 Provides-Extra: dev
 Requires-Dist: pytest>=8.0.0; extra == "dev"
 Requires-Dist: ruff>=0.8.0; extra == "dev"
+Provides-Extra: viz
+Requires-Dist: matplotlib>=3.8; extra == "viz"
 Dynamic: license-file
 
-# MathematicalMethods MCP Server
+# Mathematical/Numerical Methods - MCP Server
 
 [![MCP Server](https://badge.mcpx.dev?type=server)](https://modelcontextprotocol.io/introduction)
 [![License](https://img.shields.io/github/license/agmonetti/mathmethods-mcp)](LICENSE)
 [![CI](https://github.com/agmonetti/mathmethods-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/agmonetti/mathmethods-mcp/actions/workflows/ci.yml)
+[![npm version](https://img.shields.io/npm/v/@agmonetti/mathmethods-mcp)](https://www.npmjs.com/package/@agmonetti/mathmethods-mcp)
 [![PyPI](https://img.shields.io/pypi/v/mathmethods-mcp)](https://pypi.org/project/mathmethods-mcp/)
+[![M8ven Live Monitored](https://m8ven.ai/badge/mcp/agmonetti-mathmethods-mcp-1l7999)](https://m8ven.ai/mcp/agmonetti-mathmethods-mcp-1l7999)
+[![Mathmethods Mcp on AI Agents Listing](https://aiagentslisting.com/mathmethods-mcp/badge.svg?claim=ca81a89d96e8b011f557e77f0d8b7717)](https://aiagentslisting.com/mcp/mathmethods-mcp)
 
 A [Model Context Protocol](https://modelcontextprotocol.io) server that exposes a
 numerical-methods core as tools an LLM agent can call directly from a chat
@@ -30,17 +40,70 @@ numerical-methods engine of the academic project `modeladoYsimulacion-web`
 (UADE); the math core is **vendored** into this repository so the server is
 fully self-contained.
 
-## Quick start
+## Installation and Usage
 
+### 1. Run with NPX (Recommended)
+
+Runs on-demand without any global installation:
+
+#### Claude Code (One-liner CLI)
 ```bash
-claude mcp add mathmethods-mcp -- uvx mathmethods-mcp
+claude mcp add mathmethods npx -y @agmonetti/mathmethods-mcp
 ```
 
-Any MCP client registers the server with the same one-liner command —
-`uvx mathmethods-mcp` (a Python package that needs no cloning, venv or paths):
+#### Claude Desktop & Cursor (JSON Configuration)
+Add to your `claude_desktop_config.json` or `.cursor/mcp.json`:
 
 ```json
-{ "command": "uvx", "args": ["mathmethods"] }
+{
+  "mcpServers": {
+    "mathmethods": {
+      "command": "npx",
+      "args": ["-y", "@agmonetti/mathmethods-mcp"]
+    }
+  }
+}
+```
+
+---
+
+### 2. Install Globally from NPM
+
+Ideal for instant startup without network latency on every invocation:
+
+```bash
+npm install -g @agmonetti/mathmethods-mcp
+```
+
+```json
+{
+  "mcpServers": {
+    "mathmethods": {
+      "command": "mathmethods-mcp"
+    }
+  }
+}
+```
+
+---
+
+### 3. Run with UVX (Direct Python)
+
+Any MCP client can also run the Python package directly with Astral's `uvx`:
+
+```bash
+claude mcp add mathmethods-mcp -- uvx mathmethods-mcp
+```
+
+```json
+{
+  "mcpServers": {
+    "mathmethods": {
+      "command": "uvx",
+      "args": ["mathmethods-mcp"]
+    }
+  }
+}
 ```
 
 <details>
@@ -48,14 +111,14 @@ Any MCP client registers the server with the same one-liner command —
 
 ```bash
 git clone https://github.com/agmonetti/mathmethods-mcp.git
-cd mathmethods
+cd mathmethods-mcp
 uv sync --extra dev
-uv run mathmethods
+uv run server.py
 ```
 
-Every client config below also works with
+Every client config above also works with
 `uv run --frozen --project <checkout> python <checkout>/server.py` in place of
-`uvx mathmethods-mcp`.
+`npx -y @agmonetti/mathmethods-mcp` or `uvx mathmethods-mcp`.
 </details>
 
 ## Tools
@@ -124,13 +187,38 @@ Math expressions use Python/SymPy syntax: `x**2`, `sin(x)`, `exp(x)`,
 and the caret `^` for powers. The Greek combat parameters of Lanchester use the
 Unicode symbols `α β γ ε μ δ`.
 
+## Plots (optional)
+
+Every tool accepts a `plot=False | True` flag. With `plot=True` the response
+contains the usual JSON **plus** a rendered PNG (an MCP image content block):
+phase portraits, solution curves, bifurcation diagrams, Monte Carlo
+convergence, and so on.
+
+```text
+"Solve y' = y, y(0)=1 on [0,1] with RK4 and show me the plot."
+```
+
+Plotting needs the optional `viz` extra (Matplotlib), which is **not** part of
+the default install so the stdio server startup stays light:
+
+```bash
+pip install "mathmethods-mcp[viz]"    # pip
+uvx --from "mathmethods-mcp[viz]" mathmethods-mcp   # uv
+uv sync --extra viz                   # from a checkout
+```
+
+If `plot=True` is used without the extra, the tool returns a clear error telling
+you how to install it. Clients that do not render images still receive the JSON
+result alongside the image, so nothing is lost.
+
 ## Project layout
 
 ```
-modelo-mat-mcp/
+mathmethods-mcp/
 ├── server.py                 # FastMCP app + all tools
 ├── mathmethods/
 │   ├── compiler.py           # hardened expression validation (whitelist, caps)
+│   ├── plots.py              # optional PNG rendering (plot=True), lazy matplotlib
 │   ├── server.py             # FastMCP app and tool definitions
 │   └── core/                 # vendored math core (from modeladoYsimulacion-web)
 │       ├── root_finding.py   ├── integration.py
@@ -140,7 +228,7 @@ modelo-mat-mcp/
 │       ├── dynamic_2d_non_homogeneous.py ├── dynamic_2d_nonlinear.py
 │       ├── dynamic_2d_conservative.py ├── dynamic_2d_lanchester.py
 │       └── utils.py
-├── tests/                    # test_tools.py + test_dynamic_tools.py
+├── tests/                    # test_tools.py + test_dynamic_tools.py + test_plots.py
 ├── mcp.example.json          # server registration template (copy to .vscode/mcp.json)
 ├── requirements.txt
 └── pyproject.toml
@@ -149,7 +237,7 @@ modelo-mat-mcp/
 ## Install
 
 ```bash
-cd modelo-mat-mcp
+cd mathmethods-mcp
 python3 -m venv venv
 source venv/bin/activate
 pip install -r requirements.txt
@@ -198,12 +286,12 @@ Create `.vscode/mcp.json` (git-ignored) — or copy `mcp.example.json`:
 ```json
 {
   "servers": {
-    "modelo-mat-stdio": {
+    "mathmethods-stdio": {
       "type": "stdio",
-      "command": "uvx",
-      "args": ["mathmethods"]
+      "command": "npx",
+      "args": ["-y", "@agmonetti/mathmethods-mcp"]
     },
-    "modelo-mat-http": {
+    "mathmethods-http": {
       "type": "http",
       "url": "http://127.0.0.1:8000/mcp"
     }
@@ -225,9 +313,9 @@ Add the entry under `context_servers` (note: **not** `mcp_servers`) in
 ```json
 {
   "context_servers": {
-    "modelo-mat": {
-      "command": "uvx",
-      "args": ["mathmethods"]
+    "mathmethods": {
+      "command": "npx",
+      "args": ["-y", "@agmonetti/mathmethods-mcp"]
     }
   }
 }
@@ -247,9 +335,9 @@ global `~/.config/opencode/opencode.jsonc`:
 ```json
 {
   "mcp": {
-    "modelo-mat": {
+    "mathmethods": {
       "type": "local",
-      "command": ["uvx", "mathmethods"],
+      "command": ["npx", "-y", "@agmonetti/mathmethods-mcp"],
       "enabled": true
     }
   }
@@ -259,7 +347,7 @@ global `~/.config/opencode/opencode.jsonc`:
 Or register it with the CLI (equivalent):
 
 ```bash
-opencode mcp add modelo-mat -- uvx mathmethods-mcp
+opencode mcp add mathmethods -- npx -y @agmonetti/mathmethods-mcp
 ```
 
 For a remote server running on `http://127.0.0.1:8000/mcp`:
@@ -267,7 +355,7 @@ For a remote server running on `http://127.0.0.1:8000/mcp`:
 ```json
 {
   "mcp": {
-    "modelo-mat": {
+    "mathmethods": {
       "type": "remote",
       "url": "http://127.0.0.1:8000/mcp",
       "enabled": true
@@ -289,9 +377,9 @@ Add the entry under `mcpServers` in the Antigravity config file, typically
 ```json
 {
   "mcpServers": {
-    "modelo-mat": {
-      "command": "uvx",
-      "args": ["mathmethods"]
+    "mathmethods": {
+      "command": "npx",
+      "args": ["-y", "@agmonetti/mathmethods-mcp"]
     }
   }
 }
@@ -315,9 +403,9 @@ then inside the session:
 
 ```text
 /mcp add
-  Server name:  modelo-mat
+  Server name:  mathmethods
   Server type:  1 (Local/STDIO)
-  Command:      uvx mathmethods-mcp
+  Command:      npx -y @agmonetti/mathmethods-mcp
 ```
 
 Press `Ctrl+S` to save. The settings are stored in
@@ -333,15 +421,15 @@ Both use the `mcpServers` format. In Claude Desktop, edit
 `claude_desktop_config.json`; in Claude Code:
 
 ```bash
-claude mcp add mathmethods-mcp -- uvx mathmethods-mcp
+claude mcp add mathmethods npx -y @agmonetti/mathmethods-mcp
 ```
 
 ```json
 {
   "mcpServers": {
-    "modelo-mat": {
-      "command": "uvx",
-      "args": ["mathmethods"]
+    "mathmethods": {
+      "command": "npx",
+      "args": ["-y", "@agmonetti/mathmethods-mcp"]
     }
   }
 }

mathmethods_mcp-0.1.0/mathmethods_mcp.egg-info/PKG-INFO → mathmethods_mcp-0.2.0/README.md

@@ -1,27 +1,12 @@
-Metadata-Version: 2.4
-Name: mathmethods-mcp
-Version: 0.1.0
-Summary: MCP server exposing numerical-methods tools: bisection, Simpson 1/3, Runge-Kutta 4, Lagrange interpolation
-License-Expression: MIT
-Project-URL: Repository, https://github.com/agmonetti/mathmethods-mcp
-Requires-Python: >=3.10
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: mcp[cli]==1.14.1
-Requires-Dist: numpy>=1.26.0
-Requires-Dist: sympy>=1.12.0
-Requires-Dist: scipy>=1.11.0
-Provides-Extra: dev
-Requires-Dist: pytest>=8.0.0; extra == "dev"
-Requires-Dist: ruff>=0.8.0; extra == "dev"
-Dynamic: license-file
-
-# MathematicalMethods MCP Server
+# Mathematical/Numerical Methods - MCP Server
 
 [![MCP Server](https://badge.mcpx.dev?type=server)](https://modelcontextprotocol.io/introduction)
 [![License](https://img.shields.io/github/license/agmonetti/mathmethods-mcp)](LICENSE)
 [![CI](https://github.com/agmonetti/mathmethods-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/agmonetti/mathmethods-mcp/actions/workflows/ci.yml)
+[![npm version](https://img.shields.io/npm/v/@agmonetti/mathmethods-mcp)](https://www.npmjs.com/package/@agmonetti/mathmethods-mcp)
 [![PyPI](https://img.shields.io/pypi/v/mathmethods-mcp)](https://pypi.org/project/mathmethods-mcp/)
+[![M8ven Live Monitored](https://m8ven.ai/badge/mcp/agmonetti-mathmethods-mcp-1l7999)](https://m8ven.ai/mcp/agmonetti-mathmethods-mcp-1l7999)
+[![Mathmethods Mcp on AI Agents Listing](https://aiagentslisting.com/mathmethods-mcp/badge.svg?claim=ca81a89d96e8b011f557e77f0d8b7717)](https://aiagentslisting.com/mcp/mathmethods-mcp)
 
 A [Model Context Protocol](https://modelcontextprotocol.io) server that exposes a
 numerical-methods core as tools an LLM agent can call directly from a chat
@@ -30,17 +15,70 @@ numerical-methods engine of the academic project `modeladoYsimulacion-web`
 (UADE); the math core is **vendored** into this repository so the server is
 fully self-contained.
 
-## Quick start
+## Installation and Usage
 
+### 1. Run with NPX (Recommended)
+
+Runs on-demand without any global installation:
+
+#### Claude Code (One-liner CLI)
 ```bash
-claude mcp add mathmethods-mcp -- uvx mathmethods-mcp
+claude mcp add mathmethods npx -y @agmonetti/mathmethods-mcp
 ```
 
-Any MCP client registers the server with the same one-liner command —
-`uvx mathmethods-mcp` (a Python package that needs no cloning, venv or paths):
+#### Claude Desktop & Cursor (JSON Configuration)
+Add to your `claude_desktop_config.json` or `.cursor/mcp.json`:
 
 ```json
-{ "command": "uvx", "args": ["mathmethods"] }
+{
+  "mcpServers": {
+    "mathmethods": {
+      "command": "npx",
+      "args": ["-y", "@agmonetti/mathmethods-mcp"]
+    }
+  }
+}
+```
+
+---
+
+### 2. Install Globally from NPM
+
+Ideal for instant startup without network latency on every invocation:
+
+```bash
+npm install -g @agmonetti/mathmethods-mcp
+```
+
+```json
+{
+  "mcpServers": {
+    "mathmethods": {
+      "command": "mathmethods-mcp"
+    }
+  }
+}
+```
+
+---
+
+### 3. Run with UVX (Direct Python)
+
+Any MCP client can also run the Python package directly with Astral's `uvx`:
+
+```bash
+claude mcp add mathmethods-mcp -- uvx mathmethods-mcp
+```
+
+```json
+{
+  "mcpServers": {
+    "mathmethods": {
+      "command": "uvx",
+      "args": ["mathmethods-mcp"]
+    }
+  }
+}
 ```
 
 <details>
@@ -48,14 +86,14 @@ Any MCP client registers the server with the same one-liner command —
 
 ```bash
 git clone https://github.com/agmonetti/mathmethods-mcp.git
-cd mathmethods
+cd mathmethods-mcp
 uv sync --extra dev
-uv run mathmethods
+uv run server.py
 ```
 
-Every client config below also works with
+Every client config above also works with
 `uv run --frozen --project <checkout> python <checkout>/server.py` in place of
-`uvx mathmethods-mcp`.
+`npx -y @agmonetti/mathmethods-mcp` or `uvx mathmethods-mcp`.
 </details>
 
 ## Tools
@@ -124,13 +162,38 @@ Math expressions use Python/SymPy syntax: `x**2`, `sin(x)`, `exp(x)`,
 and the caret `^` for powers. The Greek combat parameters of Lanchester use the
 Unicode symbols `α β γ ε μ δ`.
 
+## Plots (optional)
+
+Every tool accepts a `plot=False | True` flag. With `plot=True` the response
+contains the usual JSON **plus** a rendered PNG (an MCP image content block):
+phase portraits, solution curves, bifurcation diagrams, Monte Carlo
+convergence, and so on.
+
+```text
+"Solve y' = y, y(0)=1 on [0,1] with RK4 and show me the plot."
+```
+
+Plotting needs the optional `viz` extra (Matplotlib), which is **not** part of
+the default install so the stdio server startup stays light:
+
+```bash
+pip install "mathmethods-mcp[viz]"    # pip
+uvx --from "mathmethods-mcp[viz]" mathmethods-mcp   # uv
+uv sync --extra viz                   # from a checkout
+```
+
+If `plot=True` is used without the extra, the tool returns a clear error telling
+you how to install it. Clients that do not render images still receive the JSON
+result alongside the image, so nothing is lost.
+
 ## Project layout
 
 ```
-modelo-mat-mcp/
+mathmethods-mcp/
 ├── server.py                 # FastMCP app + all tools
 ├── mathmethods/
 │   ├── compiler.py           # hardened expression validation (whitelist, caps)
+│   ├── plots.py              # optional PNG rendering (plot=True), lazy matplotlib
 │   ├── server.py             # FastMCP app and tool definitions
 │   └── core/                 # vendored math core (from modeladoYsimulacion-web)
 │       ├── root_finding.py   ├── integration.py
@@ -140,7 +203,7 @@ modelo-mat-mcp/
 │       ├── dynamic_2d_non_homogeneous.py ├── dynamic_2d_nonlinear.py
 │       ├── dynamic_2d_conservative.py ├── dynamic_2d_lanchester.py
 │       └── utils.py
-├── tests/                    # test_tools.py + test_dynamic_tools.py
+├── tests/                    # test_tools.py + test_dynamic_tools.py + test_plots.py
 ├── mcp.example.json          # server registration template (copy to .vscode/mcp.json)
 ├── requirements.txt
 └── pyproject.toml
@@ -149,7 +212,7 @@ modelo-mat-mcp/
 ## Install
 
 ```bash
-cd modelo-mat-mcp
+cd mathmethods-mcp
 python3 -m venv venv
 source venv/bin/activate
 pip install -r requirements.txt
@@ -198,12 +261,12 @@ Create `.vscode/mcp.json` (git-ignored) — or copy `mcp.example.json`:
 ```json
 {
   "servers": {
-    "modelo-mat-stdio": {
+    "mathmethods-stdio": {
       "type": "stdio",
-      "command": "uvx",
-      "args": ["mathmethods"]
+      "command": "npx",
+      "args": ["-y", "@agmonetti/mathmethods-mcp"]
     },
-    "modelo-mat-http": {
+    "mathmethods-http": {
       "type": "http",
       "url": "http://127.0.0.1:8000/mcp"
     }
@@ -225,9 +288,9 @@ Add the entry under `context_servers` (note: **not** `mcp_servers`) in
 ```json
 {
   "context_servers": {
-    "modelo-mat": {
-      "command": "uvx",
-      "args": ["mathmethods"]
+    "mathmethods": {
+      "command": "npx",
+      "args": ["-y", "@agmonetti/mathmethods-mcp"]
     }
   }
 }
@@ -247,9 +310,9 @@ global `~/.config/opencode/opencode.jsonc`:
 ```json
 {
   "mcp": {
-    "modelo-mat": {
+    "mathmethods": {
       "type": "local",
-      "command": ["uvx", "mathmethods"],
+      "command": ["npx", "-y", "@agmonetti/mathmethods-mcp"],
       "enabled": true
     }
   }
@@ -259,7 +322,7 @@ global `~/.config/opencode/opencode.jsonc`:
 Or register it with the CLI (equivalent):
 
 ```bash
-opencode mcp add modelo-mat -- uvx mathmethods-mcp
+opencode mcp add mathmethods -- npx -y @agmonetti/mathmethods-mcp
 ```
 
 For a remote server running on `http://127.0.0.1:8000/mcp`:
@@ -267,7 +330,7 @@ For a remote server running on `http://127.0.0.1:8000/mcp`:
 ```json
 {
   "mcp": {
-    "modelo-mat": {
+    "mathmethods": {
       "type": "remote",
       "url": "http://127.0.0.1:8000/mcp",
       "enabled": true
@@ -289,9 +352,9 @@ Add the entry under `mcpServers` in the Antigravity config file, typically
 ```json
 {
   "mcpServers": {
-    "modelo-mat": {
-      "command": "uvx",
-      "args": ["mathmethods"]
+    "mathmethods": {
+      "command": "npx",
+      "args": ["-y", "@agmonetti/mathmethods-mcp"]
     }
   }
 }
@@ -315,9 +378,9 @@ then inside the session:
 
 ```text
 /mcp add
-  Server name:  modelo-mat
+  Server name:  mathmethods
   Server type:  1 (Local/STDIO)
-  Command:      uvx mathmethods-mcp
+  Command:      npx -y @agmonetti/mathmethods-mcp
 ```
 
 Press `Ctrl+S` to save. The settings are stored in
@@ -333,15 +396,15 @@ Both use the `mcpServers` format. In Claude Desktop, edit
 `claude_desktop_config.json`; in Claude Code:
 
 ```bash
-claude mcp add mathmethods-mcp -- uvx mathmethods-mcp
+claude mcp add mathmethods npx -y @agmonetti/mathmethods-mcp
 ```
 
 ```json
 {
   "mcpServers": {
-    "modelo-mat": {
-      "command": "uvx",
-      "args": ["mathmethods"]
+    "mathmethods": {
+      "command": "npx",
+      "args": ["-y", "@agmonetti/mathmethods-mcp"]
     }
   }
 }

{mathmethods_mcp-0.1.0 → mathmethods_mcp-0.2.0}/mathmethods/__init__.py

@@ -4,4 +4,4 @@ Exposes the vendored numerical-methods core as Model Context Protocol (MCP)
 tools for LLM agents.
 """
 
-__version__ = "0.1.0"
+__version__ = "0.2.0"