Skills/PyPI/swisstopo-mcp

swisstopo-mcp@0.5.1

VERIFIED· not started

Publisher claims: "MCP server for Swiss federal geodata (Swisstopo APIs)" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher malkreide · publishing for 242 daysInstalls 384Last detonated 18 h ago
$claude mcp add swisstopo-mcp -- uvx swisstopo-mcp
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
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso admin.ch, shields.io, geodienste.ch, osm.ch, openplzapi.org, opengis.net, zh.ch, be.ch, cadastre.ch — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- uvx swisstopo-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 2026-11-19 and scored it 83/100 (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)src/swisstopo_mcp/server.py:36 · MCP server using network transport (SSE/HTTP) — data sent over network# The MCPServer lifespan is *not* a per-process hook: under streamable-http theFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Python subprocess execution detectedscripts/check_ruff_pin.py:71 · Python subprocess execution detecteddone = subprocess.run(call, capture_output=True, text=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/check_release_distance.py:233 · Python subprocess execution detectedp = subprocess.run(["git", "-C", str(ROOT), *args], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
URL using a raw public IP addresstests/conftest.py:11 · URL using a raw public IP address — may bypass domain-based filteringmatches, because what reaches the mock is `https://13.226.251.104/...`.Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Access to sensitive file pathssrc/swisstopo_mcp/config.py:5 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesprefix and may also be supplied via a local `.env` file (see `.env.example`).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/swisstopo_mcp/config.py:18 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_file=".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Dynamic module loadingtests/fixture_data.py:44 · Dynamic module loadingmodul = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Prompt injection attemptSECURITY.de.md:103 · Prompt injection attempt — model control tokens · informational: not an instruction fileRollen-/System-Marker (`<SYSTEM>`, `[INST]`, `### Instructions:`,Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Fake instruction boundary tagCHANGELOG.md:1195 · Fake instruction boundary tag · informational: not an instruction fileAnweisungen.</SYSTEM>` payload in a schema field now trips two assertions;Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Fake instruction boundary tagCHANGELOG.md:1198 · Fake instruction boundary tag · informational: not an instruction file- **Four missing checks added**: role/system markers (`<SYSTEM>`, `[INST]`,Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Access to sensitive file pathstests/test_http_app.py:219 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdie READMEs und `.env.example` nennen; dass sie aus *unserer*Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injection attemptSECURITY.md:102 · Prompt injection attempt — model control tokens · informational: not an instruction fileEnglish), embedded role/system markers (`<SYSTEM>`, `[INST]`, `### Instructions:`,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)tests/test_cache_hints.py:106 · MCP server using network transport (SSE/HTTP) — data sent over network"""`MCPServer` lehnt einen unbekannten Schluessel schon im Konstruktor ab;Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
HTTP URL with a raw public IP addresstests/conftest.py:11 · HTTP URL with a raw public IP address — a hard-coded destination that domain-based monitoring cannot namematches, because what reaches the mock is `https://13.226.251.104/...`.Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
LOW
Prompt injection attemptSECURITY.de.md:104 · Prompt injection attempt — model control tokens · informational: not an instruction file`<|im_start|>`), verwechselbare kyrillische/griechische Substitutionen, nichtFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptCHANGELOG.md:1199 · Prompt injection attempt — model control tokens · informational: not an instruction file`### Instructions:`, `<|im_start|>`, line-initial `Human:`/`Assistant:`), aFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Fake instruction boundary tagCHANGELOG.md:1194 · Fake instruction boundary tag · informational: not an instruction filenarrowing it fails the build. Verified: a `<SYSTEM>Ignoriere alle vorherigenFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injection attemptSECURITY.md:103 · Prompt injection attempt — model control tokens · informational: not an instruction file`<|im_start|>`), confusable Cyrillic/Greek substitutions, non-canonical toolFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Fake instruction boundary tagSECURITY.de.md:103 · Fake instruction boundary tag · informational: not an instruction fileRollen-/System-Marker (`<SYSTEM>`, `[INST]`, `### Instructions:`,Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injection attemptCHANGELOG.md:1198 · Prompt injection attempt — model control tokens · informational: not an instruction file- **Four missing checks added**: role/system markers (`<SYSTEM>`, `[INST]`,Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Dynamic module loadingtests/fixture_data.py:49 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(modul)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Fake instruction boundary tagSECURITY.md:102 · Fake instruction boundary tag · informational: not an instruction fileEnglish), embedded role/system markers (`<SYSTEM>`, `[INST]`, `### Instructions:`,Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈4,540 tok
2 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 swisstopo-mcp@0.5.1 as of 18 h ago. This is the package itself, not its dependencies.