Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.IvandeMurard/paris-compass-mcp

NPM · PARIS-COMPASS-MCP · SCANNED SEP 24

Paris commercial premises from open data: shopfront history, street turnover, sourced figures.

Available components

+3 this week 78 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 104 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability66
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1389 tokens (~231/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management70
  • Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the io.github.IvandeMurard/paris-compass-mcp server?

io.github.IvandeMurard/paris-compass-mcp runs locally as an npm package, launched with npx -y paris-compass-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · paris-compass-mcp

# add to Claude Code
claude mcp add ivandemurard-paris-compass-mcp -- npx -y paris-compass-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "ivandemurard-paris-compass-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "paris-compass-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "ivandemurard-paris-compass-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "paris-compass-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add ivandemurard-paris-compass-mcp -- npx -y paris-compass-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ivandemurard-paris-compass-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "paris-compass-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add ivandemurard-paris-compass-mcp --command npx --arg -y --arg paris-compass-mcp
# ~/.hermes/config.yaml
mcp_servers:
  ivandemurard-paris-compass-mcp:
    command: "npx"
    args: ["-y", "paris-compass-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "ivandemurard-paris-compass-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "paris-compass-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add ivandemurard-paris-compass-mcp -t stdio -c npx -a -y paris-compass-mcp
// mcp.json
{
  "mcpServers": {
    "ivandemurard-paris-compass-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "paris-compass-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 23 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

  • 21 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 +4
    • Stability: unverified → 0.27 ▲ functional
  • 4 Sept 26 +15
    • Malware scan: unverified → pass ▲ security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 24 Sept 2026 · Analysed npm/paris-compass-mcp@0.1.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 104 packages
Packages resolved 104
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 6 exposed · ~1,389 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
compare_locations ~193

Scores two points with score_location's method and returns both sets side by side, plus a per-axis numeric delta (b minus a). No combined verdict: a single score would average axes that pull in opposite directions for different trades, which is exactly what this product refuses to do (PERIMETRE.md §4).

NameTypeReqDescription
aobjectyesFirst location
bobjectyesSecond location
radius_mnumber–Search radius in metres, applied to BOTH points so the two score sets stay comparable. Capped at 2000 (compass_max_radius_m).
vintage_year––BDCom survey year for the premises layer. Only 2023 is ODbL: 2017 and 2020 carry an APUR licence that has not been read, so a public caller receives neither their contents nor their counts, and the s…

No output schema declared.

No examples provided.

explain_score ~324

Full detail on a single axis of score_location — value, source, licence, date, method and caveat — as a sentence and as structured data. Use after score_location to justify one figure rather than re-deriving it from the full response.

NameTypeReqDescription
latnumberyesLatitude. Bornée à l'emprise réelle de Paris (48,8156–48,9022), mesurée sur les 80 quartiers. Un point dans ces bornes peut malgré tout être hors du recensement — Boulogne, Levallois, Saint-Mandé et…
lngnumberyesLongitude. Bornée à l'emprise réelle de Paris (2,2241–2,4698), mesurée sur les 80 quartiers. Voir la remarque sur la latitude : la boîte est un rectangle, le corpus ne l'est pas.
metricstringyesWhich axis of score_location to explain in detail.
radius_mnumber–Search radius in metres. Pass the same value score_location was called with, otherwise the explanation describes a different question. Capped at 2000 (compass_max_radius_m).
vintage_year––BDCom survey year for the premises layer. Only 2023 is ODbL: 2017 and 2020 carry an APUR licence that has not been read, so a public caller receives neither their contents nor their counts, and the s…

No output schema declared.

No examples provided.

find_premises ~336

Ground-floor premises surveyed by APUR's door-to-door BDCom census near a point, each with the location_id that trace_premise takes. Returns candidates, not a single match: premises routinely share an address and a coordinate, so picking one is the caller's decision. Vintage 2023 only (the sole ODbL vintage) — a premise that stopped being retail before 2023 is not listed here, and trace_premise is where its earlier life shows up.

NameTypeReqDescription
latnumberyesLatitude. Bornée à l'emprise réelle de Paris (48,8156–48,9022), mesurée sur les 80 quartiers. Un point dans ces bornes peut malgré tout être hors du recensement — Boulogne, Levallois, Saint-Mandé et…
limitinteger–Maximum premises returned, capped at 200. `total_matched` carries the count BEFORE this cut, so a truncated answer still has its denominator.
lngnumberyesLongitude. Bornée à l'emprise réelle de Paris (2,2241–2,4698), mesurée sur les 80 quartiers. Voir la remarque sur la latitude : la boîte est un rectangle, le corpus ne l'est pas.
radius_mnumber–Search radius in metres. Capped at 500, well below the 2000 the database allows: this call identifies a shopfront, it does not describe a neighbourhood. Widen it only when the coordinates are approxi…

No output schema declared.

No examples provided.

list_sources ~37

Every dataset the Compass tools actually draw from, with licence and freshness. Not a marketing list — only sources a tool call here will really touch.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

score_location ~341

Scores one point on five amenity categories (schools, healthcare, groceries, parks, transit), walkability, a footfall proxy, and a road-noise proxy — each figure carrying its source, licence, date and method. No single score out of 100: PERIMETRE.md refuses one on the grounds that weights depend on the trade, so axes are returned separately.

NameTypeReqDescription
latnumberyesLatitude. Bornée à l'emprise réelle de Paris (48,8156–48,9022), mesurée sur les 80 quartiers. Un point dans ces bornes peut malgré tout être hors du recensement — Boulogne, Levallois, Saint-Mandé et…
lngnumberyesLongitude. Bornée à l'emprise réelle de Paris (2,2241–2,4698), mesurée sur les 80 quartiers. Voir la remarque sur la latitude : la boîte est un rectangle, le corpus ne l'est pas.
radius_mnumber–Search radius in metres. Capped at 2000 — beyond that the question stops being 'this neighbourhood' (compass_max_radius_m).
vintage_year––BDCom survey year for the premises layer (occupancy, vacancy). Only 2023 is ODbL: 2017 and 2020 carry an APUR licence that has not been read, so a public caller receives neither their contents nor th…

No output schema declared.

No examples provided.

trace_premise ~158

Everything known about one premise in chronological order: APUR BDCom survey rows (2017, 2020, 2023) and BODACC legal notices — business sales with their published price, safeguard, receivership and liquidation proceedings. Every row carries the record it came from, its evidence, and a derived confidence level with the rule that produced it. Answers 'has a restaurant ever been here', 'has this unit already changed use', 'was there a vacant spell', and 'what did the business last sell for'. Takes a location_id from find_premises.

NameTypeReqDescription
location_idintegeryesA location_id returned by find_premises. Not a BDCom `ordre` and not a SIRET.

No output schema declared.

No examples provided.

Common questions

What is the io.github.IvandeMurard/paris-compass-mcp server?

io.github.IvandeMurard/paris-compass-mcp is listed in the public MCP registry as io.github.IvandeMurard/paris-compass-mcp. Paris commercial premises from open data: shopfront history, street turnover, sourced figures. This page covers its npm package (paris-compass-mcp).

Is the io.github.IvandeMurard/paris-compass-mcp server safe to use?

io.github.IvandeMurard/paris-compass-mcp scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 24 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.IvandeMurard/paris-compass-mcp server expose?

io.github.IvandeMurard/paris-compass-mcp exposes 6 tools: list_sources, score_location, compare_locations, explain_score, find_premises, trace_premise. Their descriptions and schemas cost roughly 1,389 tokens of context every time the server is loaded.

Is the io.github.IvandeMurard/paris-compass-mcp server still maintained?

io.github.IvandeMurard/paris-compass-mcp is still listed as active in the MCP registry. We last reached this channel on 24 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.IvandeMurard/paris-compass-mcp server under?

io.github.IvandeMurard/paris-compass-mcp declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.