Osmosis Apply
This MCP server provides intelligent code merging capabilities through the Osmosis-Apply-1.7B model via Ollama, enabling AI assistants to apply targeted edits to existing code while preserving exact formatting and structure. Built using Python with comprehensive file operation support, it offers a single edit_snippet tool that accepts original code and edit instructions using '// ... existing code ...' markers to indicate preserved sections, with optional direct file modification capabilities that search for original code patterns and replace them in-place. The implementation features streaming response support for real-time feedback, robust error handling for file permissions and missing content, and extensive test coverage including edge cases like malformed responses and permission errors, making it valuable for automated code refactoring workflows, AI-assisted development environments, and building coding assistants that need precise code modification capabilities without breaking existing functionality.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- search
- Source
- PulseMCP
- Repository
- github.com/osmosis-ai/osmosis-apply-1.7b-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Osmosis Apply from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.