Skip to main content
mcpSource-backed

Serena MCP Server for Claude

Serena is an open-source coding-agent toolkit by Oraios that gives Claude semantic, symbol-level code tools backed by language servers, so it can find, read, and edit code precisely instead of pasting whole files.

by Oraios · submitted by glorydavid03023·added 2026-06-03·
Review first review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Safety notes
Serena can read and modify files in the project you point it at, including applying symbol-level code edits, so run it on code you can review and version-control., Depending on configuration it can run language servers and execute project commands; only enable it on trusted projects and review its actions., Operate it against a version-controlled working tree so any automated edits can be inspected and reverted through normal diff review.
Privacy notes
Project source code, file paths, and symbol information are read into the model context so Serena can reason about and edit the codebase., Avoid pointing it at directories that contain secrets or private data you do not want surfaced to the model.
Author
Oraios
Submitted by
glorydavid03023
Claim status
unclaimed
Last verified
2026-06-03

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context
Selected

0

Current score

78

Baseline

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Complete

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done
  • Source provenance statusRequired

    Marked as source-backed.

    Done
  • Metadata reviewed

    Registry metadata indicates a reviewed listing.

    Done

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done
  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done
  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done
  • Package verification flag

    No package verification flag provided.

    Pending
  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending
  • Baseline comparison available

    No baseline peer selected yet.

    Pending
  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

CLI install

Copy-ready — paste the snippet to get started.

5 minutes

Adoption plan

Balanced adoption plan

Current risk score 16/100. Use staged verification before broader rollout.

Risk 16

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done
  • Confirm metadata review state

    Listing has review metadata.

    Done
  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done
  • Review privacy notesRequired

    Privacy notes are present.

    Done
  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending
  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending
  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Required evidence gates are covered (5/6 signals complete).

Risk 15

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Present

Review metadata is present.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required evidence gates are covered for this preset.

Decision timeline

Decision timeline · balanced

5/6 steps complete with no blocking gaps for this preset.

Risk 14

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is available.

Done

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

No required blockers for this timeline preset.

Prerequisite readiness

Prerequisite readiness

4 prerequisites to line up before setup.

0/4 ready
Install & runtime1Network & hosting1General25 minutes

Safety & privacy surface

Safety & privacy surface

3 safety and 2 privacy notes across 4 risk areas. Review closely: credentials & tokens.

4 areas
  • SafetyLocal filesSerena can read and modify files in the project you point it at, including applying symbol-level code edits, so run it on code you can review and version-control.
  • SafetyExecution & processesDepending on configuration it can run language servers and execute project commands; only enable it on trusted projects and review its actions.
  • SafetyGeneralOperate it against a version-controlled working tree so any automated edits can be inspected and reverted through normal diff review.
  • PrivacyLocal filesProject source code, file paths, and symbol information are read into the model context so Serena can reason about and edit the codebase.
  • PrivacyCredentials & tokensAvoid pointing it at directories that contain secrets or private data you do not want surfaced to the model.

Safety notes

  • Serena can read and modify files in the project you point it at, including applying symbol-level code edits, so run it on code you can review and version-control.
  • Depending on configuration it can run language servers and execute project commands; only enable it on trusted projects and review its actions.
  • Operate it against a version-controlled working tree so any automated edits can be inspected and reverted through normal diff review.

Privacy notes

  • Project source code, file paths, and symbol information are read into the model context so Serena can reason about and edit the codebase.
  • Avoid pointing it at directories that contain secrets or private data you do not want surfaced to the model.

Prerequisites

  • The uv toolchain installed (provides uvx; install from https://docs.astral.sh/uv)
  • Claude Code or Claude Desktop with MCP support
  • A local project or codebase you want Serena to index and operate on
  • Internet access on first run so uvx can fetch Serena from its Git repository

Schema details

Install type
cli
Troubleshooting
Yes
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
5 minutes
Difficulty
intermediate
Full copyable content
{
  "serena": {
    "command": "uvx",
    "args": [
      "--from",
      "git+https://github.com/oraios/serena",
      "serena",
      "start-mcp-server",
      "--context",
      "ide-assistant"
    ]
  }
}

About this resource

Content

Serena turns Claude into a coding agent that works at the level of symbols rather than raw text. Instead of pasting entire files into context, Serena uses language servers to find symbols, trace where they are referenced, and apply precise edits to the right definition. That keeps context focused, reduces the chance of broad and risky rewrites, and lets Claude navigate a real codebase the way an IDE does. It is open source and free, and it works across the languages its underlying language servers support.

Features

  • Semantic, symbol-level code retrieval backed by language servers rather than plain text search.
  • Find symbols and the places that reference them to understand impact before changing code.
  • Apply targeted edits to a specific symbol or definition instead of rewriting whole files.
  • Keeps model context focused by pulling in only the relevant code, not entire files.
  • Works across many programming languages through the language servers it integrates.
  • Open source under an MIT license and runs locally as a standard MCP server.

Use Cases

  • Navigate an unfamiliar codebase by jumping between symbols and their references.
  • Perform focused refactors that touch a single definition and its call sites.
  • Investigate the blast radius of a change before applying it.
  • Let Claude make precise, reviewable edits in a real project under version control.
  • Reduce context bloat on large repositories by retrieving only relevant code.

Installation

Claude Code

  1. Install the uv toolchain (provides uvx) from https://docs.astral.sh/uv.
  2. Run: claude mcp add serena -- uvx --from git+https://github.com/oraios/serena serena start-mcp-server --context ide-assistant
  3. Verify the server is registered: claude mcp list
  4. Open a project and ask Claude to find a symbol to confirm Serena is active.

Claude Desktop

  1. Install the uv toolchain so uvx is available on your PATH.
  2. Open your Claude Desktop configuration file.
  3. Add the Serena server to the mcpServers section using the configuration below.
  4. Restart Claude Desktop and confirm the server appears.

Configuration

{
  "serena": {
    "command": "uvx",
    "args": [
      "--from",
      "git+https://github.com/oraios/serena",
      "serena",
      "start-mcp-server",
      "--context",
      "ide-assistant"
    ]
  }
}

Examples

Navigate to a symbol

Ask Claude to locate a definition instead of searching text.

"Find the definition of the AuthService class and show me its methods."

Trace references before refactoring

Understand impact before changing a function.

"Find everywhere that calls parseConfig so I can see what a signature change would affect."

Apply a focused edit

Let Serena change a single definition rather than a whole file.

"Update the body of the validateToken function to add an expiry check, and leave the rest of the file unchanged."

Security

  • Serena can read and modify files in the project you target, including applying code edits, so only run it on codebases you control and can review.
  • Run it against a version-controlled working tree so automated changes show up in diffs and can be reverted.
  • Depending on configuration it may start language servers or run project commands; enable it only on trusted projects.
  • Do not point it at directories holding secrets or private data you do not want read into the model context.

Troubleshooting

uvx is not found

Install the uv toolchain from https://docs.astral.sh/uv and confirm uvx --version works. uvx is required because Serena is distributed as a Python project rather than an npm package.

First run is slow or fails to fetch Serena

The initial launch resolves Serena from its Git repository, which needs internet access and a working uv cache. Retry once the network is available; subsequent runs reuse the cached install.

Language features or symbol lookups do not work

Serena relies on language servers for the project's language. Make sure the project is one Serena can index and that any required language tooling is available in the environment.

Server not listed in Claude Code

Re-run the claude mcp add serena ... command, then claude mcp list. Confirm it was added to the scope (project versus user) you are running in, and that the working directory points at the project you want to analyze.

Source citations

Add this badge to your README

Show that Serena MCP Server for Claude is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/serena-mcp-server.svg)](https://heyclau.de/entry/mcp/serena-mcp-server)

How it compares

Serena MCP Server for Claude side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

1 trust signal differ across this comparison (Submitter).

Field

Serena is an open-source coding-agent toolkit by Oraios that gives Claude semantic, symbol-level code tools backed by language servers, so it can find, read, and edit code precisely instead of pasting whole files.

Open dossier

Go MCP server that launches an existing stdio language server and exposes semantic code-navigation tools such as definitions, references, hover, diagnostics, symbol rename, and file edits.

Open dossier

Local-first codebase intelligence MCP server that indexes repositories with tree-sitter, stores searchable chunks in DuckDB, and gives Claude semantic search, regex search, daemon status, and deep code research tools.

Open dossier

Local code indexing MCP server that lets AI assistants search repositories, build symbol indexes, inspect file summaries, monitor changes, and navigate multi-language codebases.

Open dossier
Next steps
Trust
Review statusReviewedMaintainer reviewedReviewedMaintainer reviewedReviewedMaintainer reviewedReviewedMaintainer reviewed
Package trustPackage not verifiedPackage not verifiedPackage not verifiedPackage not verified
Source provenanceSource-backedSource-backedSource-backedSource-backed
SubmitterDiffersglorydavid03023oktofeesh1oktofeesh1oktofeesh1
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
BrandChunkHound logoChunkHound
Categorymcpmcpmcpmcp
SourceSource-backedSource-backedSource-backedSource-backed
AuthorOraiosisaacphiChunkHoundjohnhuang316
Added2026-06-032026-06-052026-06-062026-06-06
Platforms
Harness
Source repo
Safety notesSerena can read and modify files in the project you point it at, including applying symbol-level code edits, so run it on code you can review and version-control. Depending on configuration it can run language servers and execute project commands; only enable it on trusted projects and review its actions. Operate it against a version-controlled working tree so any automated edits can be inspected and reverted through normal diff review.The server can expose write-capable tools such as symbol rename and structured file edits in addition to read-only navigation tools. It launches the configured language server process with the provided workspace and environment, so review PATH, arguments, environment variables, and workspace scope. Language servers may execute project-specific discovery, indexing, build-script, or plugin behavior depending on the ecosystem and configuration. Keep manual review on rename and edit operations in large workspaces because a language server can change many references across a project. The README describes the project as beta software; expect behavior and compatibility to evolve.ChunkHound reads source files, Markdown, text, PDFs, and supported config files under the target directory and stores indexed chunks in a local database. Realtime indexing and daemon mode can continue watching project files after the initial MCP connection. Code research and web search tools require embedding, reranking, and LLM configuration and may invoke local CLIs or external model APIs depending on settings. Exclude generated files, vendored dependencies, secrets, large artifacts, and unrelated repositories before indexing broad workspace roots. Review MCP client configuration carefully when using an absolute project path in a global Claude Desktop config.Code Index MCP reads repository files, builds shallow and deep indexes, exposes file summaries, and can return source snippets through search and file resources. Point `--project-path` at one approved repository; avoid broad parent directories, home directories, generated dependency trees, or secret-heavy paths. Deep indexing and watcher refreshes can consume CPU, memory, disk IO, and temp storage on large codebases. The server can create and clear index/cache settings and temporary directories used for stored index data. Search results, file summaries, and symbol bodies can surface credentials, private code, customer data, internal URLs, or proprietary implementation details if they exist in the repository.
Privacy notesProject source code, file paths, and symbol information are read into the model context so Serena can reason about and edit the codebase. Avoid pointing it at directories that contain secrets or private data you do not want surfaced to the model.Tool results can expose source code, definitions, references, hover text, diagnostics, file paths, module names, package names, build configuration, and generated edits. Language-server logs, MCP client transcripts, model prompts, and debug output can retain proprietary code structure and project metadata. Environment variables passed to the language server may include paths, cache locations, tokens, private registry settings, or build-system credentials. Avoid connecting private workspaces to shared MCP clients or model providers without approval from the project owner.Indexed chunks, file paths, symbols, comments, Markdown, PDFs, configuration values, database files, daemon state, and search results can reveal proprietary source code and internal architecture. Embedding, reranking, LLM, and web search providers may receive code-derived queries or snippets if configured. Local ChunkHound database files, logs, daemon state, and MCP transcripts may retain code-derived context after the session ends. Avoid sharing ChunkHound databases, config files with API keys, verbose logs, research outputs, and screenshots from private repositories.Tool calls may expose file paths, filenames, source code snippets, imports, classes, methods, functions, symbols, search matches, complexity summaries, and project settings. Index data and temp directories can persist derived repository structure or symbol metadata outside the source tree. File watcher status, exclude patterns, and settings can reveal local project layout and development conventions. If an MCP client forwards tool results to a model provider, repository contents and search snippets may leave the local machine. Exclude secrets, generated artifacts, vendored dependencies, build output, and private data before indexing.
Prerequisites
  • The uv toolchain installed (provides uvx; install from https://docs.astral.sh/uv)
  • Claude Code or Claude Desktop with MCP support
  • A local project or codebase you want Serena to index and operate on
  • Internet access on first run so uvx can fetch Serena from its Git repository
  • Go installed for building the `mcp-language-server` binary.
  • A stdio language server installed for the target language, such as gopls, rust-analyzer, pyright, typescript-language-server, or clangd.
  • A workspace path the agent is allowed to inspect and, if enabled, edit.
  • Language-server environment variables, PATH entries, caches, module paths, and compile-command directories configured for the target project.
  • Python 3.10 or newer and the `uv` package manager.
  • A local repository or workspace you are authorized to index.
  • ChunkHound JSON config reviewed for database path, excludes, embeddings, and LLM provider settings.
  • Optional embedding provider credentials for semantic search, or regex-only usage when no embedding key is configured.
  • Python 3.10 or newer.
  • uv or another Python package runner that can install `code-index-mcp`.
  • An approved repository path that the MCP client is allowed to inspect.
  • Optional native search tools such as ripgrep, ugrep, ag, or grep for faster search backends.
Install
claude mcp add serena -- uvx --from git+https://github.com/oraios/serena serena start-mcp-server --context ide-assistant
go install github.com/isaacphi/mcp-language-server@latest
uv tool install chunkhound
uvx code-index-mcp --project-path ABSOLUTE_PATH_TO_REPOSITORY
Config
{
  "mcpServers": {
    "serena": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/oraios/serena",
        "serena",
        "start-mcp-server",
        "--context",
        "ide-assistant"
      ],
      "type": "stdio"
    }
  }
}
{
  "mcpServers": {
    "language-server": {
      "command": "mcp-language-server",
      "args": [
        "--workspace",
        "WORKSPACE_PATH",
        "--lsp",
        "typescript-language-server",
        "--",
        "--stdio"
      ]
    }
  }
}
{
  "mcpServers": {
    "chunkhound": {
      "command": "chunkhound",
      "args": ["mcp", "/path/to/approved/project"]
    }
  }
}
Manual-only setup:
uvx code-index-mcp --project-path ABSOLUTE_PATH_TO_REPOSITORY
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Related guides

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.