Skip to main content
Glama
noeffred

Matplotlib MCP Server

by noeffred

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MAX_AXESNoMaximum number of axes.16
MAX_BINSNoMaximum number of bins.200
MAX_ROWSNoMaximum number of rows.10000
MAX_WORKNoMaximum estimated work.5000000
MCP_HOSTNoServer bind address.127.0.0.1
MCP_PORTNoServer bind port.8000
LOG_LEVELNoControls Uvicorn's non-access logs.
MAX_CALLSNoMaximum number of calls.128
MAX_ARTISTSNoMaximum number of artists.10000
MAX_COLUMNSNoMaximum number of columns.50
MCP_API_KEYYesBearer token required for every HTTP request. Must be at least 16 characters long.
MAX_GEOMETRYNoMaximum generated geometry.250000
MAX_DATA_BYTESNoMaximum data size in bytes.1048576
MCP_THEME_PATHNoPath to a theme YAML file./etc/matplotlib-mcp/theme.yaml
MAX_IMAGE_WIDTHNoMaximum image width in pixels.1600
MAX_LABEL_CHARSNoMaximum number of label characters.500
MAX_IMAGE_HEIGHTNoMaximum image height in pixels.1600
MAX_IMAGE_PIXELSNoMaximum number of image pixels.1000000
MAX_REQUEST_BYTESNoMaximum request size in bytes.4194304
MCP_ALLOWED_HOSTSNoComma-separated list of accepted HTTP Host header values.localhost:8000,127.0.0.1:8000,matplotlib-mcp:8000
RENDER_JSON_DEPTHNoHTTP JSON nesting limit, checked before decoding.64
RENDER_QUEUE_SIZENoMaximum waiting chart/large-body requests (plus one active request).50
MAX_ARRAY_ELEMENTSNoMaximum number of array elements.250000
MAX_CONTOUR_LEVELSNoMaximum number of contour levels.200
RENDER_JSON_TOKENSNoHTTP JSON structural-token budget, checked before decoding.250000
RENDER_QUEUE_BYTESNoAggregate retained HTTP request-body bytes, including partial bodies and active requests.33554432
RENDER_BODY_SECONDSNoTotal deadline to receive the HTTP body after authentication and reader admission.10
RENDER_MEMORY_BYTESNoRenderer virtual address-space cap, applied before importing plotting libraries.268435456
RENDER_QUEUE_SECONDSNoMaximum wait before admission.30
RENDER_RECYCLE_CHARTSNoCompleted requests before replacing the renderer.50
RENDER_TIMEOUT_SECONDSNoDeadline including renderer startup, validation, rendering, and IPC.10

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources