A zero-dependency, in-memory graph database providing a memory layer for local AI agents with AST-based dependency tracking and Token-Level Provenance via Source Maps. Runs locally from the mcp-context-graph Python package.
★not rated 2 2mo agoA
tokens not measured
originalMIT
A directory-as-context standard plus a read-only MCP server that gives AI agents live, structured, token-budgeted awareness of a multi-project workspace. Runs locally from the agenticscope npm package.
★not rated 2 3mo agoA
tokens not measured
originalMIT
MCP server "fast-browser-mcp" as configured in ingjohnfigueroablanco/Fast-browser-MCP. Runs fast_browser_mcp with python. Needs 1 environment variable to run.
Almond - MCP server for Rhino 8 with a semantic scene layer: curated furniture/drawing/diagram libraries, audited Karamba capsules, structured retrieval (SQLite FTS5 + R-tree scene ledger), and a TCP bridge into Rhino (RhinoAlmondBridge, port 5000). Runs locally from the almond-mcp Python package.
★not rated 2 6d agoA
tokens not measured
originalMIT
MCP server "resolve-studio-control" as configured in Mandrilsquad1441/codex-davinci-resolve-mcp. Launched with davinci-resolve-mcp. Needs 1 environment variable to run.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Hard ground truth for CSS — extracts the browser's rendered layout as deterministic, diffable text so coding agents stop guessing. MCP server + CLI. Runs locally from the csstruth npm package.
Work a running OrcaSlicer from Claude or any MCP client: load models, tune settings, slice, and understand the result through per-feature breakdowns, setting explanations, and physics checks. Runs locally from the orcaslicer-mcp Python package.
★not rated 2 19d agoA
tokens not measured
originalMIT