An MCP server that gives AI assistants four local, read-only tools from Kanibal Studio (ALTA VISTA360, S.L.U.):
Tool | What it does |
| France only: tells whether a consent to telephone canvassing is still valid under décret 2026-662. Fail-closed. |
| Ranks B2B lead sources, from CSV text, on cost per kept qualified meeting instead of cost per lead. |
| GDPR gap report for customer service outsourced outside the EU/EEA. Not legal advice. |
| Picks the lowest declared cost rank among the capable, available and authorised models of a supplied catalogue. |
Each tool computes from its arguments only: no network call, no file access, no state kept between calls. All four are marked read-only and closed-world for MCP clients. They wrap the published packages demarchage-consent, cost-per-kept-meeting, rgpd-offshore-check and least-cost-capable.
claude mcp add kanibal-tools -- uvx kanibal-tools-mcpRelated MCP server: linkedin-prospection-mcp
Add this server to the client's MCP configuration:
{
"mcpServers": {
"kanibal-tools": {
"command": "uvx",
"args": ["kanibal-tools-mcp"]
}
}
}Without uv, install it with pip install kanibal-tools-mcp and use kanibal-tools-mcp as
the command. The server speaks MCP over stdio and needs Python 3.10 or newer.
"Is a telemarketing consent collected on 2025-11-02 still valid today?"
"Here is my CSV of lead sources for October: rank them by cost per kept meeting."
"Prepare a GDPR gap report for our customer service in Tunisia: we have SCCs but no transfer impact assessment."
"From this model catalogue, which is the cheapest one that can do Python and debugging?"
The consent tool applies French rules only (décret 2026-662). It is a check, not legal advice.
The GDPR report is a checklist: a report without blocking gap is not a finding of compliance.
A low cost per kept meeting does not prove profitability.
The model selection uses only the facts in the catalogue you supply; it does not switch models, call providers or guarantee savings.
pip install -e ".[dev]"
pytestThe tests call every tool through an in-memory MCP client session.
Prepared by Kanibal Studio, associated with ALTA VISTA360, S.L.U. Our public sites are Altavista360, Altavista Conseil and K-Pulse.
Licensed under the MIT License.
France only: is a consent to telephone canvassing still valid under décret 2026-662?
Returns "valide", "expire" (older than the ceiling), "revoque" (any sign of
revocation wins) or "preuve_manquante" (no readable collection date, or one in the
future), with the expiry date and proof-retention date. Fail-closed. Use it for
French telemarketing consent only; for transfers of customer-service data outside
the EU use gdpr_offshore_gap_report. Not legal advice.
Inputs: collected_at (required), now, revoked_at, max_age_days. Returns: object
GDPR gap report for customer-service processing outsourced outside the EU/EEA.
Checks the transfer basis (adequacy or Art. 46 safeguards), the transfer impact
assessment, the Art. 28 processor contract and its twelve clauses, Art. 32 security
controls and breach notification. Only a JSON true satisfies a check; anything else
is a gap or "to_verify". Use it for transfers outside the EU; for French
telemarketing consent use check_telemarketing_consent. Not legal advice and not a
certification: a report without blocking gap is not a finding of compliance.
Inputs: answers (required), lang. Returns: object
Rank B2B lead sources on cost per kept qualified meeting instead of cost per lead.
Returns, per source and period, total cost, cost per lead, show rate, cost per kept meeting, cost per qualified kept meeting, and cost per deal and margin minus cost when provided. Invalid rows are reported as a tool error naming each row. Use it to compare acquisition channels; it does not check consent or GDPR. A low cost per meeting does not prove profitability.
Inputs: csv_text (required), min_meetings. Returns: object
Pick, from a supplied catalogue, the model with the lowest declared cost rank among those that have every required capability and are available and authorised.
Returns status "selected" with the comparison basis, "needs_information" naming the
missing or non-comparable evidence, or "no_candidate_in_catalogue", plus exclusions. Use it to choose
between AI models from facts you supply; it is unrelated to lead sources. Nothing
is called, switched or launched; savings are not guaranteed.
Inputs: catalogue (required). Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 4 tools
Each tool targets a completely different question: French telemarketing consent validity, lead-source cost ranking, GDPR offshore transfer gaps, and model selection. The descriptions go further and explicitly name the sibling tool to use instead when the user's intent differs (e.g. check_telemarketing_consent vs gdpr_offshore_gap_report, and 'unrelated to lead sources' on the model picker), which removes any realistic risk of misselection.
Three of four names are verb-first snake_case (check_, rank_, select_), which gives a readable pattern, but gdpr_offshore_gap_report is a bare noun phrase with no verb, breaking the convention. It is still unambiguous and self-descriptive, so the deviation is minor rather than confusing.
Four tools is on the thin side, but each is a substantial, self-contained analysis with non-trivial inputs and outputs rather than a trivial wrapper. The count fits a small personal utility belt, though the set is a grab-bag of unrelated domains rather than a single coherent product surface.
Individually each tool covers its own scope well, with fail-closed semantics and explicit caveats (not legal advice, no guarantee), but the set has no shared domain or lifecycle, so there is no notion of a 'complete' surface — no tool links consent evidence to lead economics or to the GDPR report, and there are no read/export/list operations around any of the analyses.
Curated EU AI/Sec/DevTools/Fintech B2B leads, Claude-scored. MCP+x402. Free 250/mo.
Local business & Google Maps B2B lead extractor MCP: phone, email, website, DNS & SaaS tech stack.
335 MCP tools, 75 playbooks. AI-native CRM, email/SMS, events, OAuth.
AI legal compliance: contract review, risk scoring, EU/CN AI act, watermark check. 8 MCP tools.
