Skip to content

Code Execution MCP Server

Serena

A fully-featured coding agent that relies on symbolic code operations by using language servers.

Scan flagged something by oraios21,594MITPythonIntermediatestdio
View on GitHub Install Guide

Install

No auto-install command available for this server.

Check the GitHub repository for setup instructions

Safety Report

67% Scan flagged something
Scanned 5 months ago
4 passed 2 warnings
Security
Authentication
details

Authentication detected: env_required, auth_header

Pass
CORS Policy
details

No CORS-relevant transport detected (likely stdio)

N/A
Rate Limiting
details

No rate limiting mechanism detected

Info
Known CVEs
details

No known CVEs in dependencies

Pass
Code Quality
Dependency Audit
details

No known vulnerable dependencies detected

Pass
Dangerous Patterns
details

Dangerous patterns detected: os_system_py, subprocess_shell

Warning
License
details

License: MIT

Pass
Community
Maintenance Status
details

Last commit 5 months ago

Warning

Learn about our security methodology →

Compatibility

Claude Desktop
Not Tested
Claude Code
Not Tested
Cursor
Not Tested
VS Code
Not Tested

Tools Provided (39)

find_symbol

Perform global or local symbol search across the codebase using the language server.

find_referencing_symbols

Locate all symbols that reference a given symbol via the language server (find usages).

get_symbols_overview

Retrieve all top-level symbols (classes, functions, variables) defined in a file.

insert_after_symbol

Insert new code content immediately after a symbol definition.

insert_before_symbol

Insert new code content immediately before a symbol definition.

rename_symbol

Refactor a symbol name across the entire codebase using language server rename.

replace_symbol_body

Replace the complete body of a symbol definition with new content.

restart_language_server

Restart the language server (optional tool, useful when the LSP enters a bad state).

create_text_file

Create a new text file with given content.

read_file

Read the contents of a file.

delete_lines

Delete specific line ranges from a file.

insert_at_line

Insert content at a specific line number in a file.

list_dir

List the contents of a directory.

find_file

Search for files by name or pattern within the project.

replace_content

Replace text content within a file using string matching.

replace_lines

Replace a specific line range in a file with new content.

search_for_pattern

Search for a regex or text pattern across project files.

execute_shell_command

Execute a shell command in the project context and return its output.

activate_project

Activate a configured project in Serena by name.

get_current_config

Get the current Serena configuration and active project settings.

open_dashboard

Open the Serena web dashboard for project management.

remove_project

Remove a project from Serena's configuration.

switch_modes

Switch Serena between different operating modes (e.g., editing vs. read-only).

read_memory

Read a named memory file from Serena's persistent memory store.

write_memory

Write content to a named memory file in Serena's persistent memory store.

edit_memory

Edit an existing memory file in Serena's persistent store.

delete_memory

Delete a named memory file from Serena's persistent store.

list_memories

List all memory files currently stored in Serena.

rename_memory

Rename a memory file in Serena's persistent store.

onboarding

Run the Serena onboarding workflow to set up a new project.

check_onboarding_performed

Check whether onboarding has been completed for the current project.

initial_instructions

Retrieve the initial instructions and system prompt for the current project context.

prepare_for_new_conversation

Reset Serena's state to prepare for a fresh conversation context.

query_project

Access information from a configured external project.

list_queryable_projects

List all external projects that are configured and available to query.

jet_brains_find_symbol

Search symbols using JetBrains IDE backend (optional, requires JetBrains plugin).

jet_brains_find_referencing_symbols

Find referencing symbols via JetBrains IDE backend.

jet_brains_get_symbols_overview

Retrieve file-level symbol overview using JetBrains IDE backend.

jet_brains_type_hierarchy

Show supertypes and subtypes for a symbol using JetBrains IDE backend.

Frequently Asked Questions

What is Serena?

A fully-featured coding agent that relies on symbolic code operations by using language servers.

What tools does Serena provide?

Serena provides 39 tools including find_symbol, find_referencing_symbols, get_symbols_overview, insert_after_symbol. Each tool can be called by AI agents to perform specific operations.

Is Serena safe to use?

We cannot tell you that, and nobody scanning at this scale can. What we did in March 2026 was shallow-clone Serena and run five keyword searches over its source: auth identifiers, CORS configuration, rate-limit identifiers, the dependency manifest against a hardcoded list of 18 known-vulnerable packages, and unguarded eval/exec calls. At least one matched — the specific finding is in the scan report on this page. A text search cannot follow a variable, judge intent, or tell you what a server does once it is running, so "nothing matched" is not "safe". What the scan does and does not cover is written out at /mcp/security.

What are alternatives to Serena?

Similar MCP servers include MCP Run Python, DesktopCommanderMCP, Container Use. Each serves a similar purpose but may differ in features, language, and compatibility.

Similar MCP Servers

MCP Run Python

Scan flagged something
by pydantic

Run Python code in a secure sandbox via MCP tool calls

code execution Python stdio
15.5k 1 tools
View

DesktopCommanderMCP

Scan flagged something
by wonderwhy-er

A swiss-army-knife that can manage/execute programs and read/write/search/edit code and text files.

code execution TypeScript stdio
claude mcp add desktopcommandermcp -- npx -y desktop-commander
5.7k 25 tools
View

Container Use

Not scanned
by dagger

Containerized environments for coding agents. Multiple agents can work independently, isolated in fresh containers and git branches. No conflicts, many experiments. Full execution history, terminal access to agent environments, git workflow. Any agent/model/infra stack.

code execution Go stdio
3.6k 13 tools
View
Was this helpful?

Free AI writing tools

Check a draft for AI tells, then fix what the check finds.

Stay Updated on MCP Servers

New servers, safety alerts, and install guides — weekly.