pulsemcp Safe content atomic mcp-remote

Agent Knowledge

This MCP server provides AI knowledge management capabilities through Elasticsearch integration, file system operations, and version control, offering 31 specialized tools across document indexing with schema validation, comprehensive file operations within sandboxed directories, and Git/SVN version control workflows. Built by the Agent Knowledge MCP Contributors using Python with strict security controls and configurable validation modes, it features auto-setup capabilities for Elasticsearch via Docker, document template creation for knowledge bases, path normalization and security restrictions, and flexible configuration management with backward compatibility for deprecated tools. The implementation supports cross-platform operations with robust error handling, making it valuable for building AI assistants that need structured knowledge storage, automated document management workflows, and version-controlled file operations without manual database or file system navigation.

Cognium trust score
50%
Tier
Unverified

Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.

View full trust & usage report →

Metadata

Version
1.0.0
Skill type
atomic
Execution layer
mcp-remote
Category
database
Source
PulseMCP
Author type
human
Updated
2026-04-30
View source Find related skills

Use via MCP

MCP

Resolve Agent Knowledge 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
Swap --scope user for --scope project to commit it to .mcp.json.

Search SkillsRegistry