"Building voice agents and controlling SIP phones" matching MCP servers:

MCP server that analyzes codebases with tree-sitter and generates AGENTS.md files for AI agents.

Enables orchestrating multiple AI CLI agents (Claude Code, Codex, Gemini CLI, Copilot CLI) through a unified MCP interface for task delegation, cross-agent comparison, and specialized tools like code review and debugging.

Validates AGENTS.md files against the cross-vendor coding-agent spec, detecting security smells and consistency issues.

Enables AI agents to submit code files for analysis and receive rule-based findings with severities, line numbers, and SARIF fingerprints, covering security, complexity, and dependency/configuration drift.

Lets agents inspect native binaries, JavaScript/Electron applications, .NET assemblies, websites, and runtime behavior, returning evidence-backed findings and limitations for understanding and reimplementing features.

MCP server that integrates sql-sop SQL linter into LLM clients, enabling linting SQL queries and listing lint rules via chat tools.

locidx

Enables AI agents to analyze and diff binaries by driving Ghidra headless or inside its GUI, exposing native reverse-engineering tools such as listing functions and segments, searching strings, decompiling, disassembling, and following cross-references. Ships with a devcontainer and supports local stdio or remote HTTP deployment.

Enables MCP clients to load eight on-demand coding skills and inspect project repositories through bounded, read-only map, search, read, diff, checks, and style tools. It keeps context lean by loading skill bodies only when needed and limiting repository scan and output sizes.

Provides token-efficient code retrieval for coding agents by indexing repositories and enabling ranked snippet search, symbol outlines, and surgical line reads.

An MCP server that provides a semantic index and 14 bounded tools for AI agents to navigate Excel workbooks by symbols, references, and diagnostics, avoiding the need to read entire rows.

Codebase intelligence and context engine for AI coding agents: search, symbol lookup, impact analysis, and context building via MCP.

Enables building MCP servers in TypeScript where tool schemas, descriptions, and validation are automatically generated from class methods, their TypeScript types, and JSDoc comments at compile time.

Cartograph is an MCP server that provides agent-native code intelligence by building a queryable code graph from a repository using tree-sitter and SQLite. It offers tools for symbol lookup, call graph traversal, blast radius analysis, and architecture overview to help coding agents answer structural questions about code.

Automatically detects packages that can be stubbed during Python exe building and generates minimal stub code to reduce executable size.

Enables smart code search in your editor using natural language queries, building an index of your workspace.

Enables AI assistants to perform reverse engineering and debugging of Windows executables through x64dbg, with tools for loading executables, controlling execution, analyzing memory and security, and generating reports.

Enables AI agents to build React applications using JP Morgan Chase's Salt Design System by providing real-time access to component APIs, documentation, and accessibility guidelines. It supports tasks such as scaffolding new projects, building UI patterns, and converting Figma designs into Salt code via the Model Context Protocol.

Enables scanning repositories for hardcoded service URLs and clients, and building service-to-service API dependency maps.

Enables scanning code for deprecated annotations and comments, building a deprecation catalog, and tracking deprecated endpoints and features.

Enables AI assistants to safely interact with local code repositories through MCP tools for search, context building, and workspace management, while keeping all operations local and human-controlled for patch approval.

A workshop repository teaching advanced Model Context Protocol features for building AI-connected apps with deeper integration capabilities.

Enables scanning paths and pasted snippets for credential leaks, building and diffing baselines, listing rules, assessing entropy, producing SARIF, and running a demo through MCP tools.

Enables AI assistants to read, analyze, edit, and create Alteryx workflows, including summarizing workflows, finding tools, editing configurations, updating SQL, managing connections, and building new workflows programmatically.

Enables live inspection and debugging of running C++ processes (development builds with PDBs) by controlling execution through cdb, evaluating expressions with natvis, reading and writing memory, and rapidly querying symbols and types via DIA, with special support for Unreal Engine processes.

Enables coding agents to run deterministic, zero-dependency AST static analysis over source code, building call graphs and dependency metrics to find orphaned functions, unreachable methods, breaking API surface diffs, and token-bloat clusters, then return a structured refactoring plan. It plugs into MCP clients like Claude Desktop, Cursor, and Windsurf via a single Python entrypoint.

Enables multi-agent code review with P0/P1/P2 severity scoring by orchestrating locally installed AI CLIs (Claude, Codex) to perform parallel analysis, deterministic scoring, and consensus-building on git diffs.

Cloud-deployable MCP server exposing secureFlows' OpenAPI operations (tagged ai-safe/ai-optional) as MCP tools, plus static helper tools like login URL building and integration linting for coding agents.

Gives MCP clients a read-only, evidence-based view of explicitly approved local projects and individual Codex sessions, enabling codebase browsing, session review, and comparison of session records against current source and bounded Git history without modifying sources or controlling sessions.

Enables AI coding agents to query a pre-built semantic knowledge graph of code, reducing token usage and tool calls. Supports 16 tools for code exploration, analysis, and context building.