Agent Shaper extracts per-module tensor shape metadata from any PyTorch `nn.Module` and uses it to annotate source files — either with descriptive
Agent Shaper extracts per-module tensor shape metadata from any PyTorch nn.Module and uses it to annotate source files — either with descriptive shape comments or
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| dim_names | The optional dim_names parameter maps symbolic names to their concrete values in the example run. This lets the shape annotations show (B, T, n_embd) instead of (2, 16, 64). When two names share the same value (e.g. B=2 |
{
"mcpServers": {
"agent-shaper": {
"command": "/path/to/.venv/bin/python",
"args": [
"-m",
"agent_shaper.mcp_server"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
MCP server that scaffolds Chimera fuzzing test suites
Let Codex orchestrate external coding agents through their native harnesses.
Facilitates interaction with the Transport NSW API using the Model Context Protocol for accessing real-time transport data.
An MCP server for the open source MISP project