Skills/PyPI/sigil-mcp-server

sigil-mcp-server@1.0.1

VERIFIED· not started

Publisher claims: "Model Context Protocol server for IDE-like code navigation and semantic search" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher superuser666-sigil · publishing for 349 daysInstalls 65Last detonated 1 h ago
$claude mcp add sigil-mcp-server -- uvx sigil-mcp-server
WatchReport an issue

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: Verified 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_KEYSIGIL_MCP_ADMIN_API_KEYSIGIL_MCP_ADMIN_REQUIRE_API_KEYSIGIL_MCP_API_KEYSIGIL_MCP_API_KEY_FILESIGIL_MCP_AUTH_ENABLEDSIGIL_MCP_OAUTH_DIRSIGIL_MCP_OAUTH_ENABLEDSIGIL_MCP_OAUTH_REDIRECT_ALLOW_LISTSIGIL_MCP_REQUIRE_TOKENSIGIL_MCP_SERVER_TOKENConfiguration, not credentials: PYTEST_CURRENT_TEST, SIGIL_ADMIN_UI_ARGS, SIGIL_ADMIN_UI_AUTOSTART, SIGIL_ADMIN_UI_COMMAND, SIGIL_ADMIN_UI_PATH, SIGIL_ADMIN_UI_PORT, SIGIL_INDEX_PATH, SIGIL_MCP_ADMIN_ALLOWED_IPS, SIGIL_MCP_ADMIN_ENABLED, SIGIL_MCP_ADMIN_HOST, SIGIL_MCP_ADMIN_PORT, SIGIL_MCP_ALLOW_LOCAL_BYPASS, SIGIL_MCP_ALLOWED_IPS, SIGIL_MCP_AUTO_INSTALL, SIGIL_MCP_CHATGPT_COMPLIANCE_ENABLED, SIGIL_MCP_HEADER_LOGGING_ENABLED, SIGIL_MCP_HOME, SIGIL_MCP_HOST, SIGIL_MCP_HTTP_PATH, SIGIL_MCP_INDEX_WORKERS, SIGIL_MCP_LANCEDB_STUB, SIGIL_MCP_LLAMA_BATCH, SIGIL_MCP_LLAMA_N_BATCH, SIGIL_MCP_LLAMA_N_UBATCH, SIGIL_MCP_LLAMA_NO_LOG_FILTER, SIGIL_MCP_LLAMA_THREADS, SIGIL_MCP_LLAMA_THREADS_BATCH, SIGIL_MCP_LLAMACPP_N_BATCH, SIGIL_MCP_LLAMACPP_N_UBATCH
Where it talks to
no vendor host named in the codeAlso chatgpt.com — 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 chatgpt.com as well as its own vendor. The guard injects OPENAI_API_KEY, SIGIL_MCP_ADMIN_API_KEY, SIGIL_MCP_ADMIN_REQUIRE_API_KEY, SIGIL_MCP_API_KEY, SIGIL_MCP_API_KEY_FILE, SIGIL_MCP_AUTH_ENABLED, SIGIL_MCP_OAUTH_DIR, SIGIL_MCP_OAUTH_ENABLED, SIGIL_MCP_OAUTH_REDIRECT_ALLOW_LIST, SIGIL_MCP_REQUIRE_TOKEN, SIGIL_MCP_SERVER_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx sigil-mcp-server

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 2026-11-18 and scored it 81/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. 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
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

LOW
Authorization escalation languagedocs/CHATGPT_SETUP.md:36 · Authorization escalation language · informational: not an instruction fileDeveloper Mode in ChatGPT Plus allows you to connect to remote MCP servers directly without creating custom actions.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Authorization escalation languagedocs/AGENTS.md:21 · Authorization escalation language- Verify registration: `GET /admin/mcp/status` (requires admin access).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsigil_mcp/indexer.py:1966 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Prompt injectiondocs/CHATGPT_SETUP.md:34 · Prompt injection — known jailbreak technique reference · informational: not an instruction file## Method 1: Developer Mode Configuration (Recommended)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectiondocs/CHATGPT_SETUP.md:36 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileDeveloper Mode in ChatGPT Plus allows you to connect to remote MCP servers directly without creating custom actions.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
File type combined with upload actionsigil_mcp/admin_api.py:824 · File type combined with upload action — agent may exfiltrate local data filesbody = await request.json() if request.method == "POST" else {}Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Prompt injectiondocs/CHATGPT_SETUP.md:9 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileThis guide shows you how to configure your Sigil MCP server with ChatGPT using Developer Mode and a custom connector.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Python subprocess execution detectedsigil_mcp/admin_ui.py:53 · Python subprocess execution detectedself.proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Authorization escalation languagedocs/CHATGPT_SETUP.md:18 · Authorization escalation language · informational: not an instruction file- Developer Mode enabled in ChatGPTFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languagedocs/CHATGPT_SETUP.md:34 · Authorization escalation language · informational: not an instruction file## Method 1: Developer Mode Configuration (Recommended)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectiondocs/CHATGPT_SETUP.md:27 · Prompt injection — known jailbreak technique reference · informational: not an instruction file1. **Via Developer Mode** - Configure MCP server URL directly in ChatGPT settings (recommended for development)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
MCP server using network transport (SSE/HTTP)sigil_mcp/config.py:420 · MCP server using network transport (SSE/HTTP) — data sent over networkreturn str(self.get("mcp_server.http_path", "/"))Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_mcp_client_more.py:52 · MCP server using network transport (SSE/HTTP) — data sent over networkserver = ExternalMCPServer(name="srv", type="sse", url="http://example.com")Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
LOW
Authorization escalation languagedocs/external_mcp.md:69 · Authorization escalation language · informational: not an instruction file- `GET /admin/mcp/status` (admin access).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Dynamic module loadingtests/test_watcher_unit_more.py:327 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssigil_mcp/config.py:260 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"htmlcov", "env", ".env", "out", "bin", "obj",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Authorization escalation languagedocs/CLAUDE.md:21 · Authorization escalation language- Check registration: `GET /admin/mcp/status` (admin access required).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionsigil_mcp/admin_api.py:280 · File type combined with upload action — agent may exfiltrate local data filesbody = await request.json() if request.method == "POST" else {}Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedsigil_mcp/indexer.py:1953 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Dynamic module loadingtests/test_watcher_unit_more.py:325 · Dynamic module loadingmodule = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsigil_mcp/mcp_installer.py:42 · Python subprocess execution detectedsubprocess.run(cmdline, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionsigil_mcp/admin_api.py:471 · File type combined with upload action — agent may exfiltrate local data filesbody = await request.json() if request.method == "POST" else {}Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsigil_mcp/admin_api.py:357 · File type combined with upload action — agent may exfiltrate local data filesbody = await request.json() if request.method == "POST" else {}Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)sigil_mcp/config.py:415 · MCP server using network transport (SSE/HTTP) — data sent over networkreturn str(self.get("mcp_server.sse_path", "/mcp/sse"))Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
LOW
Authorization escalation languagedocs/RUNBOOK.md:1750 · Authorization escalation language · informational: not an instruction file- `GET /admin/mcp/status` (admin access) for current servers/tools/errorsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionsigil_mcp/admin_api.py:572 · File type combined with upload action — agent may exfiltrate local data filesbody = await request.json() if request.method == "POST" else {}Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Authorization escalation languagedocs/CHATGPT_SETUP.md:9 · Authorization escalation language · informational: not an instruction fileThis guide shows you how to configure your Sigil MCP server with ChatGPT using Developer Mode and a custom connector.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languagedocs/CHATGPT_SETUP.md:27 · Authorization escalation language · informational: not an instruction file1. **Via Developer Mode** - Configure MCP server URL directly in ChatGPT settings (recommended for development)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectiondocs/CHATGPT_SETUP.md:18 · Prompt injection — known jailbreak technique reference · informational: not an instruction file- Developer Mode enabled in ChatGPTFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈958 tok
3 files · 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

No advisories in OSV for sigil-mcp-server@1.0.1 as of 52 min ago. This is the package itself, not its dependencies.