Skills/PyPI/g8-mcp-server

g8-mcp-server@0.187.0

VERIFIED· not started

Publisher claims: "graph8 MCP server - GTM operations for AI agents" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher graph8-com · publishing for 258 daysInstalls 5,059Last detonated 4d ago
$claude mcp add g8-mcp-server -- uvx g8-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
EDA_JWT_TOKENENFORCE_MCP_TOKEN_AUDIENCEG8_API_KEYJWT_SECRETMCP_AUTH_PROXY_ENABLEDMCP_INTROSPECTION_CLIENT_SECRETMCP_TOKEN_REVALIDATE_TTLPROPELAUTH_API_KEYPROPELAUTH_AUTH_URLConfiguration, not credentials: APP_BASE_URL, APP_ENV, BACKEND_URL, EDA_API, ENABLE_PLAN_RATE_LIMITING, FRONTEND_URL, G8_API_URL, G8_MCP_MODE, G8_MCP_PROGRESSIVE_DISCOVERY, G8_MCP_PUBLIC_URL, G8_MCP_URL, GRAPH8_BACKEND_URL, MARKETPLACE_ORG_ID, MCP_COMPRESSION_MIN_BYTES, MCP_EDA_ACTOR, MCP_EDA_ENABLED, MCP_INBOX_MESSAGE_CHAR_LIMIT, MCP_INBOX_PREVIEW_CHARS, MCP_INTROSPECTION_CLIENT_ID, MCP_RATE_LIMIT_PER_MINUTE, MCP_RATE_LIMIT_PER_SECOND, MCP_RESPONSE_COMPRESSION, MCP_TOOL_COOKIE_DOMAIN, MODE, NEXT_PUBLIC_API_URL_GROWTH, RATE_LIMIT_PAYG_RPM, RATE_LIMIT_PAYG_RPS, RATE_LIMIT_PLATFORM_RPM, RATE_LIMIT_PLATFORM_RPS, RATE_LIMIT_TRIAL_RPM, RATE_LIMIT_TRIAL_RPS
Where it talks to
no vendor host named in the codeAlso graph8.com, propelauth-api.com, claude.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 graph8.com, propelauth-api.com, claude.ai as well as its own vendor. The guard injects EDA_JWT_TOKEN, ENFORCE_MCP_TOKEN_AUDIENCE, G8_API_KEY, JWT_SECRET, MCP_AUTH_PROXY_ENABLED, MCP_INTROSPECTION_CLIENT_SECRET, MCP_TOKEN_REVALIDATE_TTL, PROPELAUTH_API_KEY, PROPELAUTH_AUTH_URL only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx g8-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 2026-11-10 and scored it 87/100 (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

MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_cli_usage.py:7 · MCP server using network transport (SSE/HTTP) — data sent over networkcd mcp_server && uv run --no-project --with 'mcp>=1.6.0' --with httpx \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_cli_logs.py:7 · MCP server using network transport (SSE/HTTP) — data sent over networkcd mcp_server && uv run --no-project --with 'mcp>=1.6.0' --with httpx \Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Access to sensitive file pathstests/conftest.py:10 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesa populated ``.env``.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandoauth.py:109 · Process kill command — agent can terminate processes"""Front-door is ON by default; MCP_AUTH_PROXY_ENABLED=false is the kill switch.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandoauth.py:8 · Process kill command — agent can terminate processesBy default (kill switch: MCP_AUTH_PROXY_ENABLED=false) we interpose a thin,Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_app_renderer.py:77 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files{"image_id": "x2", "image_url": "file:///etc/passwd", "platform": "meta"},Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_library_tools.py:436 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesresult = await _tool_fn(server, "g8_library_get")(slug="../../etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_voice_tools.py:294 · MCP server using network transport (SSE/HTTP) — data sent over networkawait _tool(mcp_server, "g8_voice_list_missed_callbacks").fn(limit=9999)Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Access to sensitive file pathstests/test_library_tools.py:418 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert library_module.is_valid_slug("../../etc/passwd") is FalseFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_voice_tools.py:285 · MCP server using network transport (SSE/HTTP) — data sent over networkawait _tool(mcp_server, "g8_voice_list_missed_callbacks").fn()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_voice_tools.py:297 · MCP server using network transport (SSE/HTTP) — data sent over networkawait _tool(mcp_server, "g8_voice_list_missed_callbacks").fn(limit=0)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_cli_webhooks.py:6 · MCP server using network transport (SSE/HTTP) — data sent over networkcd mcp_server && uv run --no-project --with 'mcp>=1.6.0' --with httpx \Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST04

Cost to the agent

Instructions loaded
≈50 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

No advisories in OSV for g8-mcp-server@0.187.0 as of 4d ago. This is the package itself, not its dependencies.

g8-mcp-server@0.187.0 safety verdict: Verified (not started) — KillerSkills