MVR API - Minimum Viable Relationships

Validate an MVR key or the public demo key. Use only when an agent needs to confirm access mode before calling other tools.

Canonicalize the venture, market actor, country, sector, and archetype. Use first when the user gives a name or market context.

Check if there is enough evidence to decide yet and list missing proof. Use before decision_check when evidence may be thin.

Turn formal, informal, sentiment, field, and market context into safe and unsafe inferences. Use after evidence capture, before verdict.

Produce the final MVR readiness verdict, from permission_not_yet_earned to ready_to_scale. Use last, once evidence is gathered.

Market-entry guardrail for launch or expansion advice. Use before recommending entry into an African or high-context market.

MVP-advice guardrail. Use before telling a founder to build when trust, permission, embeddedness, or guardian proof is untested.

Investor memo preflight. Flags missing relational proof before funding, diligence, valuation, or investment-committee recommendations.

Accelerator screening preflight. Separate claimed traction from evidence-ready applicants before cohort selection or demo-day routing.

Local-partner readiness check. Use when the question is whether a distributor, channel, implementer, or partner is legitimate enough to rely on.

Guardian-risk scan for regulators, gatekeepers, local authorities, community custodians, or veto holders that can block execution.

Evidence gap planner. Return the next proof to request before the agent makes a stronger claim or go/no-go recommendation.

Abstention guardrail. Decide whether to refuse, soften, or caveat a confident recommendation when relational readiness is unproven.

Drop-in agent guardrail before market entry, MVP launch, scale, funding, CFO action, or partnership advice in African and high-context markets.

Market-permission memo builder. Summarize safe claims, unsafe claims, blocking dimensions, and next proof for a board or client memo.

Find public MVR-Bench dev scenarios and private-test boundaries. Use for benchmark setup, not for live market-entry advice.

Prepare an MVR-Bench run submission. Public MCP returns instructions; private leaderboard scoring stays server-side and requires authorization.

Fetch public MVR-Bench leaderboard rows, scores, and Reckless-GO Rate baselines for citation or benchmark reporting.

Explain Reckless-GO Rate: how often an agent greenlights readiness beyond evidence. Use when the user asks about the metric itself.