dodopayments/contextmcp

v0.4.0 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

Published 1mo MCP Developer Tools

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

context context-api context7 documentation mcp mcp-server

+3 more

openai pinecone self-hosted

Summary

AI summary

Added CLI flags for configurable runs and fixed embedding parameter handling.

Changes in this release

Type	Severity	Summary	CVE
Feature	Low	`clean:vectors` prompts for confirmation before deleting vectors. `clean:vectors` prompts for confirmation before deleting vectors. Source: llm_adapter@2026-06-10 Confidence: high	—
Feature	Low	`index-to-txt` script gains `--input`, `--output`, `--force`, and `--help` flags. `index-to-txt` script gains `--input`, `--output`, `--force`, and `--help` flags. Source: llm_adapter@2026-06-10 Confidence: high	—
Bugfix	Medium	OpenAI embeddings now only send `dimensions` to supported models and pass configured dimensions correctly. OpenAI embeddings now only send `dimensions` to supported models and pass configured dimensions correctly. Source: llm_adapter@2026-06-10 Confidence: high	—
Bugfix	Medium	Packaging bundles scaffold template into npm package for clean installs. Packaging bundles scaffold template into npm package for clean installs. Source: llm_adapter@2026-06-10 Confidence: high	—

Full changelog

contextmcp v0.4.0

This is a minor release. It adds new CLI flags to the scaffolded scripts and fixes several packaging and embedding bugs. All changes are backward compatible.

Features

clean:vectors now prompts for confirmation before deleting vectors, with a --force flag to skip the prompt for non-interactive use (#38).
index-to-txt script gains --input, --output, --force, and --help flags for configurable, scriptable runs (#39).

Fixes

OpenAI embeddings: only send the dimensions parameter to models that actually support it, and correctly pass the configured dimensions through to the OpenAI embedding API.
Packaging: bundle the scaffold template into the published npm package so contextmcp can scaffold projects from a clean install.

Docs & Tests

Document Gemini as a supported embedding provider.
Add a Vitest harness with unit tests for the parser core utilities.

Upgrade notes

clean:vectors is now interactive by default. If you call it from scripts or CI, pass --force to preserve the previous non-prompting behavior.

Full changelog: v0.3.1...v0.4.0

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track dodopayments/contextmcp

Get notified when new releases ship.

About dodopayments/contextmcp

Self-hosted MCP server that indexes documentation from various sources and serves it to AI Agents with semantic search.

All releases →