edt-bridge-mcp@0.45.0
VERIFIED· not startedPublisher claims: "stdio MCP front-end for the edt-bridge 1C:EDT plugin: EDT's own diagnostics, metadata and types, query validation, write tools, infobases and a debugger; proxies to a running EDT, or auto-starts a headless one" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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
EDT_BRIDGE_TOKENConfiguration, not credentials: EDT_BRIDGE_AUTOSTART, EDT_BRIDGE_EDT_DIR, EDT_BRIDGE_HEAP, EDT_BRIDGE_NO_PLUGINS, EDT_BRIDGE_PORT, EDT_BRIDGE_PORT_SCAN, EDT_BRIDGE_START_TIMEOUT, EDT_BRIDGE_TOOLSET, EDT_BRIDGE_VMARGS, EDT_BRIDGE_WINDOW_WAIT, EDT_BRIDGE_WORKSPACE, LC_ALL, ProgramFiles- Where it talks to
- no vendor host named in the codeAlso 1c.ru — 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 1c.ru as well as its own vendor. The guard injects EDT_BRIDGE_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.
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 2026-11-13 and scored it 82/100 (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 deviationsStatic findings
child = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.elif c in ", \r\n\t":Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."en": "kill the headless session when it does not stop within the timeout",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."1CV8LOG(ver 2.0)\r\n0f1e2d3c-0000-4000-8000-000000000001\r\n\r\n" + records,Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."""The keepalive shell goes first - it is the CLI's parent, so a tree kill from belowFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = subprocess.run([sys.executable, "-c", parent, json.dumps(command)],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.search let shutdown --force for one bridge kill the EDT of another. The workspace is theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.out = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.looking for the text `subprocess.run(` at the head of a call looks straight past a callableFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.run = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["taskkill", "/PID", str(pid), "/T", "/F"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.state, output = tmp_path / "state.json", tmp_path / "output.log"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."""Write junit.xml and allure-results/ of a form check report into `output`; returns their paths."""Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."rerun with --force to kill it")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.The manual routine this replaces is: find 1cedtcli in the task manager, kill it, start EDT. So theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.manager. Without --force the command says which pids are left rather than kill them."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Path(config["exitCode"]).write_text("" + exit_code + "\r\n", encoding="utf-8")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.process = subprocess.Popen(argv, cwd=log.parent, env=env, stdin=subprocess.DEVNULL, stdout=output,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.raw = subprocess.run(["powershell", "-NoProfile", "-Command", query],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.self._headless_process = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."1CV8LOG(ver 2.0)\r\n0f1e2d3c-0000-4000-8000-000000000001\r\n\r\n"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.state, output = tmp_path / "state.json", tmp_path / "output.log"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.run = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."description": "kill the headless session when it does not stop in time "Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.assert report["reports"] == {"junit": str(output / "junit.xml"), "allure": str(output / "allure-results")}Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."p=subprocess.Popen(json.loads(sys.argv[1]),stdin=subprocess.DEVNULL,"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run(["ps", "-eo", "pid=,ppid=,args="], capture_output=True, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Path(config["logging"]["file"]).write_text("" + log, encoding="utf-8")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.line is already handled as non-JSON, and a log message must never kill the process.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.raw = subprocess.run(["powershell", "-NoProfile", "-Command", query],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.state, output = tmp_path / "state.json", tmp_path / "output.log"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.# so without it the shell reports - and force would kill - its own process.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = subprocess.run(argv, capture_output=True, text=True, encoding="utf-8",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.done = subprocess.run([sys.executable, "-c", "import sys; from edt_bridge_mcp.server import main; "Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.holder = subprocess.Popen([sys.executable, "-c", code, str(lock)], stdin=subprocess.PIPE,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
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 edt-bridge-mcp@0.45.0 as of 21 h ago. This is the package itself, not its dependencies.