Skills/PyPI/relace-mcp

relace-mcp@0.2.4

CAUTION· not started

Publisher claims: "Unofficial Relace MCP Server - Fast code merging via Relace API" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher possible055 · publishing for 298 daysInstalls 233Last detonated 1 h ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
OPENAI_API_KEYRELACE_API_KEYConfiguration, not credentials: APPLY_TEMPERATURE, MCP_DOTENV_PATH, MCP_SEARCH_MODE, RELACE_API_ENDPOINT, RELACE_DEFAULT_ENCODING, RELACE_DOTENV_PATH, RELACE_REPO_ID, RELACE_REPO_LIST_MAX, RELACE_REPO_SYNC_MAX_FILES, RELACE_REPO_SYNC_TIMEOUT, RELACE_UPLOAD_MAX_WORKERS, SEARCH_LSP_TOOLS, SEARCH_TEMPERATURE, SEARCH_TOP_P
Where it talks to
relace.run (its own)Also openrouter.ai, cerebras.ai — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names openrouter.ai, cerebras.ai as well as its own vendor. The guard injects OPENAI_API_KEY, RELACE_API_KEY only into requests to relace.run (and its subdomains) and refuses the rest.

$vet-skills run --secrets OPENAI_API_KEY=relace.run,RELACE_API_KEY=relace.run -- uvx relace-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-15 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Collapsed <details> block carrying instructions; Collapsed <details> block carrying instructions; Collapsed <details> block carrying instructions. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

HIGH
Collapsed <details> block carrying instructionsREADME.md:63 · Collapsed <details> block carrying instructions<summary><strong>Claude Code</strong></summary> ```bash claude mcp add relace \ --env RELACE_API_KEY=rlc-your-api-key \ --env MCP_BASE_DIR=/absolute/path/to/youFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:97 · Collapsed <details> block carrying instructions<summary><strong>VS Code</strong></summary> `.vscode/mcp.json` ```json { "mcp": { "servers": { "relace": { "type": "stdio", "command": "uv", "args": ["tool", "rFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:75 · Collapsed <details> block carrying instructions<summary><strong>Windsurf</strong></summary> `~/.codeium/windsurf/mcp_config.json` ```json { "mcpServers": { "relace": { "command": "uv", "args": ["tool", "run"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:41 · Collapsed <details> block carrying instructions<summary><strong>Cursor</strong></summary> `~/.cursor/mcp.json` ```json { "mcpServers": { "relace": { "command": "uv", "args": ["tool", "run", "relace-mcp"], "eFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsrc/relace_mcp/tools/search/_impl/grep_search.py:314 · Python subprocess execution detectedresult = subprocess.run( # nosec B603Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/relace_mcp/server.py:40 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileslogger.info("Loaded .env from MCP_DOTENV_PATH: %s", path)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/relace_mcp/server.py:23 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""Load .env file from MCP_DOTENV_PATH or default locations.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/relace_mcp/utils.py:40 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# SECURITY: Normalize to prevent /repo//etc/passwd -> /etc/passwdFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/relace_mcp/tools/search/_impl/gitignore.py:33 · Python subprocess execution detectedresult = subprocess.run( # nosec B603 B607 - fixed command, no user inputFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/relace_mcp/tools/repo/state.py:29 · Python subprocess execution detectedresult = subprocess.run( # nosec B603 B607 - hardcoded commandFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/relace_mcp/tools/repo/state.py:354 · Python subprocess execution detectedresult = subprocess.run( # nosec B603 B607 - hardcoded commandFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/relace_mcp/tools/search/_impl/grep_search.py:191 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# path escapes (e.g., a symlink inside base_dir pointing to /etc/passwd).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Collapsed <details> block carrying instructionsREADME.md:122 · Collapsed <details> block carrying instructions<summary><strong>Codex CLI</strong></summary> `~/.codex/config.toml` ```toml [mcp_servers.relace] command = "uv" args = ["tool", "run", "relace-mcp"] [mcp_serveFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsrc/relace_mcp/tools/repo/state.py:90 · Python subprocess execution detectedresult = subprocess.run( # nosec B603 B607 - hardcoded commandFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/relace_mcp/tools/repo/state.py:47 · Python subprocess execution detectedresult = subprocess.run( # nosec B603 B607 - hardcoded commandFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/relace_mcp/tools/search/_impl/bash.py:113 · Python subprocess execution detectedresult = subprocess.run( # nosec B603 B602 B607Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/relace_mcp/tools/repo/sync.py:103 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/relace_mcp/tools/repo/sync.py:130 · Python subprocess execution detectedresult = subprocess.run( # nosec B603 B607 - hardcoded command, no user inputFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/relace_mcp/lsp/client.py:861 · Python subprocess execution detectedself._process = subprocess.Popen( # nosec B603 - trusted commandFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/relace_mcp/tools/repo/state.py:343 · Python subprocess execution detectedresult = subprocess.run( # nosec B603 B607 - hardcoded commandFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/relace_mcp/tools/search/_impl/bash.py:102 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# via wildcard expansion (e.g., `cat link*` -> `cat link_to_/etc/passwd`).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈51 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim possible055: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim possible055Propose a patch to the maintainer