lsp-mcp
Enables AI assistants to interact with VS Code's language server protocol features (definitions, references, diagnostics) and debugger (breakpoints, stepping, variable inspection) via an MCP server.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
rexl2018
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
callHierarchyFind what calls a function or what a function calls by using the function name. Perfect for understanding code flow and dependencies - faster than manually tracing through files
definitionFind the definition of a symbol by name. More efficient than searching files - instantly jumps to where a function/class/variable is defined
diagnosticsGet diagnostics (errors, warnings, info) for a file or entire workspace. Instantly see all problems without running builds - includes type errors, linting issues, and more
hierarchyTreeBuild multi-level call hierarchy tree and generate Mermaid visualization. Supports recursive analysis of function call relationships with circular reference detection.
hoverGet hover information (type info, documentation) for a symbol by name. MUCH FASTER than reading entire files when you just need to understand a function signature or type
referencesFind all references to a symbol by name. Superior to grep - finds semantic references including imports, type usage, and renamed variables
symbolSearchSearch for symbols (classes, functions, variables) across the workspace. Instant semantic search - finds exact matches unlike text-based grep
workspaceSymbolsGet a complete map of all symbols in the workspace (classes, functions, etc). ESSENTIAL for understanding codebase structure - use this instead of searching through files manually
debug_clearBreakpointsRemove all breakpoints from the workspace
debug_continueExecutionContinue execution from the current breakpoint or paused state
debug_statusGet current debug session status and configuration information
debug_evaluateExpressionEvaluate an expression in the current debug context (REPL/watch functionality). Test hypotheses instantly - execute any expression without modifying code
debug_getCallStackGet the current call stack/stack trace from the paused debug session. Understand execution flow instantly - see the complete call chain at a glance
debug_getOutputGet debug console output from the active debug session (Note: Only works with "console": "internalConsole" in launch.json, not with "integratedTerminal")
debug_inspectVariablesInspect variables in the current scope (locals, globals, etc.) during debugging. See all variable values instantly - no more hovering over each one
debug_listBreakpointsList all current breakpoints in the workspace. See all breakpoints at once - perfect for debugging complex flows
debug_listConfigurationsList available debug configurations from launch.json
debug_pauseExecutionPause the running debug session at the current execution point
debug_setBreakpointSet a breakpoint by symbol name or file/line with optional conditions. Debug smarter - set breakpoints instantly without clicking through files
debug_startSessionStart a debug session using a configuration from launch.json. Launch debugging instantly - no need to navigate to the debug panel
debug_stepIntoStep into function calls on the current line
debug_stepOutStep out of the current function and return to the caller
debug_stepOverStep over the current line of code (execute current line without entering functions)
debug_stopSessionStop the current debug session
debug_toggleBreakpointToggle a breakpoint on/off at a symbol or file/line location
refactor_renameRename a symbol across all files in the workspace. Refactor safely - automatically updates all references, imports, and type usages
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
glob CLI: Command injection via -c/--cmd executes matches with shell:true
Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
26/26 tools missing one or more hints — callHierarchy (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); definition (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); diagnostics (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +23 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.17.3 (high), @modelcontextprotocol/sdk@1.17.3 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
1 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/rexl2018/lsp-mcp)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check