jev-agent-tools-mcp
Related Servers
Alternatives to jev-agent-tools-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceIt introspects a repository and exposes guarded MCP tools over stdio, enabling clients to query code and optionally perform mutating operations when explicitly allowed.251 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables coding agents to query a parsed graph of a repository and to recall what earlier sessions learned about it, both stored in FalkorDB behind one traversal. It exposes eight MCP tools over stdio for locating symbols, tracing calls and impact paths, and writing or recalling user- and repo-scoped facts, procedures, and handoffs.303,777 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients such as Claude Desktop and Claude Code to query an indexed source repository through path-guarded tools for hybrid keyword-and-vector code search, file snippets, symbol explanations, reference lookups, and test-skeleton suggestions. Serves those results over stdio with cited file:line locations so agents can answer questions about a codebase and drive grounded code review.MIT
- AlicenseNot gradedqualityBmaintenanceProvides read-only access to NALLAR engineering evidence and portfolio artifacts over MCP, exposing tools, resources, and prompts via stdio JSON-RPC.MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to search, record, correct, and review the provenance and version history of memories, and to obtain answers composed from guarded context in which private values are replaced by placeholders and resolved locally on the device. Exposes these capabilities through dependency-free tools over stdio.MIT
- AlicenseNot gradedqualityCmaintenanceEnables people and AI agents to query local code repositories as graphs through stdio MCP tools for project listing, search, dependency tracing, impact analysis, bridge detection, node inspection, bounded code reading, and optional LSP definition/reference lookups.MIT
TDQS
Scored across 6 tools
Each tool has a distinct target: one situation (jev_ask), many files (jev_ask_files), finding files (jev_find_files), one big file (jev_locate_in_file), diffs (jev_check_diff), tests (jev_select_tests). The descriptions explicitly cross-reference each other with 'Not for →' routing, which mostly resolves overlap between the two ask tools. The very long, nearly identical boilerplate on every tool slightly blurs the boundaries in practice, keeping it from a 5.
All six tools share the jev_ prefix followed by a clear verb_noun pattern (jev_ask, jev_ask_files, jev_find_files, jev_locate_in_file, jev_check_diff, jev_select_tests). The convention is uniform and readable throughout.
Six tools is well-scoped for a semantic-judgment server covering distinct stages (find, locate, ask, diff review, test selection). Each tool earns its place without redundancy.
The surface covers discovery (find/locate), judgment (ask/ask_files), and review (check_diff/select_tests) — a coherent lifecycle for its purpose. Minor gaps exist (e.g. no explicit summarization or symbol-level lookup, left to native tools), but the core workflow is covered.