trpc-mcp@1.0.0
VERIFIED· install onlyPublisher claims: "TRPC MCP implementation" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 8 of 25 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
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
- no credential variables read in the code
- Where it talks to
- no vendor host named in the code
- What we saw when it ran
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Connect it under the guard. Bundled scripts ran with no arguments; no agent task scenario for this bundle. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
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; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 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 deviationsStatic findings
sudo rm -rf .__*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.ps aux | grep "trpc_main" | grep -v grep | awk '{print $2}' | xargs kill -9Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.assert captured["url"] == "http://10.0.0.1:9000/mcp"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls._STATEFUL = McpServerConfig(redis={"host": "x"}, settings={"stateless_http": False})Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.register_plugin(PluginType.SERVER_CODEC, TRPC_MCP_PROTOCOL, init_pos=PluginInitPos.WORKER)(TrpcMcpServerHttpCodec)Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.sudo rm -rf distFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.class TrpcMcpServerHttpCodec(ServerHttpCodec):Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.sudo rm -rf *.logFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.from trpc_mcp._codec import TrpcMcpServerHttpCodecFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.from trpc_mcp._codec import TrpcMcpServerHttpCodecFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.sudo rm -rf htmlcovFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."""TrpcMcpServer subclass that routes HTTP requests through TRPC filters."""Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.monkeypatch.setattr(tst, "get_mcp_server_config", lambda: McpServerConfig(transport=MCP_STREAMABLE_HTTP))Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them._SHARED = McpServerConfig(redis={"host": "x"}, settings={"stateless_http": True})Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.stateless_http = mcp_server.settings.get(STATELESS_HTTP, False)Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.return TrpcMcpServerHttpCodec().encode_data(ctx, b"")Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.assert not isinstance(get_server_codec("http"), TrpcMcpServerHttpCodec)Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.assert isinstance(get_server_codec(TRPC_MCP_PROTOCOL), TrpcMcpServerHttpCodec)Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.if not mcp_server.redis or stateless_http is False:Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.TrpcMcpServerHttpCodec().encode_data(ctx, b"")Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them._NO_REDIS = McpServerConfig(redis={}, settings={"stateless_http": True})Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.body = TrpcMcpServerHttpCodec().encode_data(ctx, b"payload")Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.sudo rm -rf coverage.xmlFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.f"worker_num is {worker_num}, redis: {mcp_server.redis} stateless_http: {stateless_http}, "Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.sudo rm -rf .coverageFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Not checked against OSV yet; the weekly check has not reached this version.