Enables coding agents to perform token-aware ripgrep searches and atomic multi-file edits to reduce context window usage.
Also known as BasilSkyWalk/parecode
- Stars
- 5
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.7.0
- Last commit
- Sep 14, 2026
- License
- MIT
What is parecode MCP?
parecode enables coding agents to perform token-aware ripgrep searches and atomic multi-file edits to reduce context window usage.
Summary generated from the project's README
About parecode MCP server
Coding agents that need to navigate large codebases without exhausting context windows can use parecode to perform token-aware searches and multi-file edits. By utilizing the system's ripgrep installation, the server provides tools like ParecodeSearch and ParecodeEdit that collapse multiple traditional tool calls into single, efficient operations. This approach is designed to reduce both token consumption and the number of turns required to complete complex refactoring tasks.
Developers using Claude Code can set up the server locally via npm. The installation process includes an optional SessionStart hook to prioritize these specialized tools and a parecode-explore plugin that uses a cheaper subagent for exploration-style questions. The system operates entirely on the local machine with no network calls or telemetry, ensuring that code data and session logs remain private. Users can monitor their efficiency through local session logs that estimate saved tokens.
What you can do with it
- 1Efficient multi-file refactoringAn agent can find every call site of a specific symbol across several files and apply changes to all of them in a single batch.
- 2Context-aware code explorationA developer can ask where a specific component is located or how a function works using a low-cost subagent to save main session tokens.
- 3Targeted code searchingSearch for multiple related patterns simultaneously to trace event flows without running separate grep commands.
- 4Expanding search resultsAfter finding a specific line of interest, an agent can widen the visible code range without re-reading the entire file.
Written from the project's README. Every use case is checked against a quote from it.
How to install parecode MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall parecode MCP in Claude Code
$ claude mcp add parecode -- npx -y parecodeInstall parecode MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"parecode": {
"command": "npx",
"args": [
"-y",
"parecode"
]
}
}
}Install parecode MCP in VS Code
.vscode/mcp.json
{
"servers": {
"parecode": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"parecode"
]
}
}
}Install parecode MCP in VS Code CLI
$ code --add-mcp '{"name":"parecode","type":"stdio","command":"npx","args":["-y","parecode"]}'Install parecode MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"parecode": {
"command": "npx",
"args": [
"-y",
"parecode"
]
}
}
}Install parecode MCP in Codex
$ codex mcp add parecode -- npx -y parecodeInstall parecode MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.parecode] command = "npx" args = ["-y", "parecode"]
Install parecode MCP in Gemini CLI
$ gemini mcp add -s user parecode npx -- -y parecodeInstall parecode MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"parecode": {
"command": "npx",
"args": [
"-y",
"parecode"
]
}
}
}Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablebasilskywalk/parecode is public and reachablegithub.com/basilskywalk/parecode ↗Pass
- Package names this repository as its sourceparecode names basilskywalk/parecode as sourcenpmjs.com/package/parecode ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for parecodenpmjs.com/package/parecode/v/0.7.0#provenance ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-09-14github.com/basilskywalk/parecode ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from parecodePass
- No critical advisory in the package or its dependencies114 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubparecode
An MCP server that gives coding agents context-window-aware search and safe, atomic multi-file edits — built to cut token usage on large codebases without giving up correctness.
Requirements
- Node.js 20 or newer (ESM, native test runner, stable
fetch-free runtime). - ripgrep on
PATH(rgon Linux/macOS,rg.exeon Windows). Install via your package manager:- macOS:
brew install ripgrep - Debian/Ubuntu:
apt install ripgrep - Windows:
winget install BurntSushi.ripgrep.MSVCorchoco install ripgrep
- macOS:
- A supported MCP client (Claude Code is the reference target).
Parecode does not bundle ripgrep — it shells out to the system binary so you stay on a single, audited version.
Install
npm install -g parecode
Pure JavaScript — no native dependencies, no C/C++ toolchain required.
Quick start
Register the server with Claude Code:
parecode init # user scope; installs MCP + SessionStart hook + parecode-explore plugin (defaults)
parecode init --scope project # commit MCP config + hook to the repo
parecode init --no-hook # register MCP only; skip the SessionStart hook
parecode init --no-plugin # skip the parecode-explore Claude Code plugin
parecode init --print # print the equivalent command without running it
parecode init --remove-hook # remove the SessionStart hook (MCP stays registered)
parecode init --remove-plugin # uninstall the parecode-explore Claude Code plugin
The SessionStart hook injects a short directive at the start of each session telling Claude to prefer ParecodeSearch / ParecodeEdit over the equivalent native tools. Without it, Claude's first-party Grep / Read / Edit tools typically win by default and Parecode's token savings never land. The hook payload is a static string; parecode hook session-start prints it. Pass --no-hook if you would rather opt in explicitly per session via your own tooling.
The bundled parecode-explore Claude Code plugin adds a read-only subagent (pinned to Haiku, given only ParecodeSearch) and a matching skill, so exploration-style questions ("where is X?", "how does Y work?", "find all usages of Z") get answered in a cheap, isolated context window instead of burning tokens in your main session. init registers a local marketplace pointing at the npm-installed copy and runs claude plugin install parecode-explore@parecode. If your Claude Code build doesn't support the plugin subcommand the step soft-fails with a warning and the rest of init still succeeds; pass --no-plugin to skip it entirely, or --with-plugin to make any plugin-step failure hard-fail.
Then in any session, the ParecodeSearch, ParecodeExpand, and ParecodeEdit tools become available. Run parecode doctor to confirm registration, hook status, and .codegraph/ pairing if present.
What it does
ParecodeSearch— ripgrep-backed search that returns matches with surrounding context windows in a single call, with per-file byte chunking so large result sets do not blow up your context.patternaccepts a single string or an array of strings; arrays dispatch parallel ripgrep runs sharing the samepaths/contextLines, and each match carries apatterns: string[]field listing which input patterns contributed. One call replaces N back-to-back greps for related-keyword flow tracing.- Overlapping or adjacent windows within the same file are merged automatically (gap ≤
contextLines), with bridging lines loaded from disk. - Per-match and response-level
estimatedTokensare returned so the agent can self-budget before consuming results. - Opt-in
relatedSymbols: truesurfaces likely event-flow neighbours (Handle<X>,On<X>,<X>Handler/Listener/Closed/Completed/Started) discovered in each match, capped at 10. - Omitted line ranges are reported so the agent can widen with
ParecodeExpandwithout re-reading the whole file.
ParecodeExpand— widen a known(file, startLine, endLine)range with optionalcontextBefore/contextAfterpadding. Designed as the natural follow-up to aParecodeSearchmatch. Returns the sameestimatedTokensshape so the same self-budgeting heuristic applies. Prefer this over a full-fileReadafter locating a line.ParecodeEdit— batched multi-file edits with whitespace-tolerant fuzzy matching (and an opt-in Unicode-lookalike mode), pre/poststatconflict detection, and atomic same-directory rename writes. Cross-file edits run in parallel.parecode stats— local JSONL session log with token-saved estimates. Zero network. Zero telemetry.
Measured savings
On search-and-edit tasks — finding call sites, multi-file refactors, "do X to every Y" — Parecode cut cost ~40% and assistant turns ~75–83% in matched A/B tests:
| repo | task | cost | turns |
|---|---|---|---|
| TypeScript | find every call site of a symbol, edit each (17 sites, 8 files) | −43% | −83% |
| Unity / C# | find every call site of a symbol, edit each (11 sites, 5 files) | −41% | −76% |
Method: the identical task run with Parecode on vs off, a fresh session per run, n=3 per arm with alternated order, Sonnet 4.6. Savings come from collapsing many Grep / Read / Edit round-trips into single ParecodeSearch / ParecodeEdit calls — so the win scales with how much searching and multi-file fan-out a task involves, and shrinks toward zero on single-file or reasoning-heavy tasks. These are measured per-session token and cost numbers, not the estimates in the scan below.
Retroactive Savings Scan
Curious how much Parecode would have saved you if you had installed it earlier? You can scan your past Claude Code sessions:
parecode stats --retroactive --since 30d
Sample output:
Parecode — last 30d (retroactive scan)
─────────────────────
Sessions: 42
Tool calls: 156
Calls batched (est): 89
Tokens saved (est): 1,200,000
* Note: Retroactive savings are estimated, not measured.
Privacy disclaimer: This scan runs entirely locally against Claude Code's session transcripts (~/.claude/projects/**). By default, it parses only structured fields (tool names, paths, patterns, and token counts). It does not send any data over the network. The --include-content flag (which allows reading tool input/output) is strictly opt-in and loudly flagged if used.
Privacy
Parecode performs no network calls at runtime. Session logs are written to your OS data directory (resolved via env-paths) with 0600 permissions on Unix. Logs are self-maintaining: each server start prunes session data older than 30 days and caps the envelope log at 5 MB. Prune earlier with parecode prune <days> or wipe the data dir. Update to the latest release (and refresh hooks/plugin) with parecode update.
License
parecode MCP questions
How do I add parecode MCP to Claude Code?
Run claude mcp add parecode -- npx -y parecode in your terminal. Add --scope user to make it available in every project.
How do I add parecode MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Does parecode bundle ripgrep?
No, it shells out to the system binary so you use your own audited version.
How much can I save on costs using parecode?
In matched A/B tests, it cut costs by approximately 40% and assistant turns by 75–83% on search-and-edit tasks.