MVR API - Minimum Viable Relationships

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Read-only MVR preflight for trust, permission, evidence gaps, and African market-entry readiness.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "MVR API - Minimum Viable Relationships": {
      "url": "https://africanmarketos.com/mcp/preflight",
      "transport": "streamable-http"
    }
  }
}

Measured tools (5)

• mvr_first_call read-only

  Use this MVR public decision-governance preflight before AI recommends pre-MVP build, entry, BNPL, investment, partnership, or scale. Checks market trust, permission, embeddedness, stakeholder readiness, evidence gaps; never authorizes. Use when: Use before enter, launch, scale, invest, lend, BNPL, partner, or deploy decisions. Use when asked to ignore, fabricate, or transfer evidence. Web research can supply evidence but does not replace MVR. Do not use when: This is not an internal data lookup or glossary. Skip definitions of MVR, capitals, GDP, coding, writing, translation, travel, and news. Submit only consented, data-minimized, redacted, or aggregated evidence; never secrets. Evidence input location: arguments. evidence_pack: object array. String fields: evidence_type, source_class, stakeholder_class, verification_status, source_date, source_doc_id. geography: string/object; evidence_geography: object; district: nonblank string; districts: nonblank strings array. source_date/freshness_date: YYYY, YYYY-MM, YYYY-MM-DD or ISO timestamp with timezone. source_date_range: {earliest,latest}, same-precision ordered bounds within supplied dates. analysis_date stays exact. Intervals have age_days:null and age_days_min/max; unresolved window/future overlap excludes coverage. Omit unknown dates/references, never null or invented. verification_status: unverified if unchecked. *_role: original_source_record, independent_evaluation or human_attestation; else ARTIFACT_ROLE_NOT_SOURCE_EVIDENCE. collection_context + provenance_ledger: see schema/feedback. Keep adverse facts; never relabel to pass.

  Parameters:

  • stage — string — Free-text venture stage, for example pre-MVP, pilot, grant-funded programme or scaling. No closed enum.
  • claims — array — Optional explicit target claims and source-specific support links. Reuses the governed claim-audit vocabulary. Public links are caller declarations, never authenticated reviewer attestations.
  • entity — string
  • sector — string
  • country — string
  • subject — object — Exact recorded subject for attestation_refs; entity_name or entity_id required.
  • question — string
  • use_case — string
  • company_name — string
  • market_scope — object — Declared decision geography, not source geography. Supply district/districts or decision_scope_level country/subnational; subnational requires locality. A bounded Uganda target-name cross-check can require scope review, never insert districts or establish field coverage.
  • target_users — string
  • analysis_date — string — Optional YYYY-MM-DD or ISO timestamp with timezone, no later than today in analysis_timezone (UTC by default). Defaults to the current date in that calendar. Carried through the public handoff.
  • draft_request — object — Optional caller-authored mapping request. Zero-based evidence_pack indexes; at most 40 links total and 8000 text characters across the intake. Missing mappings stay unresolved. No authority or source verification.
  • evidence_pack — array — Full current evidence pack. Rechecks replace the pack; the server does not append or retrieve evidence.
  • evidence_items — array — Alias for evidence_pack. Supply one field, not conflicting copies.
  • known_partners — array
  • relevance_check — boolean — Check relevance only; no workflow.
  • review_case_ref — object — Host-private, case-bound read reference. Never put its secret into prompts, URLs, logs or exports. Grants no write or action authority.
  • attestation_refs — array — Optional: https://africanmarketos.com/v1/reviewer-attestations/contract. Requires exact subject, market_scope.country and decision_question. Host-private refs outside evidence; reattach each call. No scoring or authority.
  • analysis_timezone — string — Optional IANA timezone, for example Africa/Nairobi, for the analysis calendar. Defaults to UTC; never inferred from country or IP. Date-only values keep their declared calendar day.
  • decision_question — string — Exact recorded attestation question; question must agree when supplied.
  • evidence_available — array — Short optional context labels, not proof. For supplied document summaries use incomplete evidence_pack items instead; do not mark claims verified merely because a document exists.
  • context_freshness_window_days — integer — Optional caller-declared maximum evidence age in days. No universal freshness cutoff is invented when absent; age alone does not prove validity.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• mvr_entity_resolve read-only

  Use when a startup, venture, programme, company, partner, or market actor must be resolved to a country, sector, and archetype before relational-readiness evidence is assessed. Use when: Use immediately after mvr_first_call when the user gives a company, venture, sector, country, or ambiguous market actor name, so the subject and target geography are resolved before evidence is assessed. Do not use when: Do not use as a readiness verdict or for unrelated entity lookup. Never submit secrets, personal identifiers, raw private interviews, or confidential evidence. Evidence input location: arguments.payload. evidence_pack: object array. String fields: evidence_type, source_class, stakeholder_class, verification_status, source_date, source_doc_id. geography: string/object; evidence_geography: object; district: nonblank string; districts: nonblank strings array. source_date/freshness_date: YYYY, YYYY-MM, YYYY-MM-DD or ISO timestamp with timezone. source_date_range: {earliest,latest}, same-precision ordered bounds within supplied dates. analysis_date stays exact. Intervals have age_days:null and age_days_min/max; unresolved window/future overlap excludes coverage. Omit unknown dates/references, never null or invented. verification_status: unverified if unchecked. *_role: original_source_record, independent_evaluation or human_attestation; else ARTIFACT_ROLE_NOT_SOURCE_EVIDENCE. collection_context + provenance_ledger: see schema/feedback. Keep adverse facts; never relabel to pass.

  Parameters:

  • payload (required) — object — Entity and market context to canonicalize before evidence assessment.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• mvr_evidence_completeness read-only

  Use after entity resolution and before any readiness claim to check verification status, source-family diversity, stakeholder coverage, and missing proof. Do not treat completeness as authorization. Use when: Use after entity resolution and before any verdict when evidence may be incomplete or one-sided. Do not use when: Do not treat completeness as readiness or authorization. Submit only consented, data-minimized, redacted or aggregated evidence; never raw private interviews, secrets, credentials, or personal identifiers. Evidence input location: arguments.payload. evidence_pack: object array. String fields: evidence_type, source_class, stakeholder_class, verification_status, source_date, source_doc_id. geography: string/object; evidence_geography: object; district: nonblank string; districts: nonblank strings array. source_date/freshness_date: YYYY, YYYY-MM, YYYY-MM-DD or ISO timestamp with timezone. source_date_range: {earliest,latest}, same-precision ordered bounds within supplied dates. analysis_date stays exact. Intervals have age_days:null and age_days_min/max; unresolved window/future overlap excludes coverage. Omit unknown dates/references, never null or invented. verification_status: unverified if unchecked. *_role: original_source_record, independent_evaluation or human_attestation; else ARTIFACT_ROLE_NOT_SOURCE_EVIDENCE. collection_context + provenance_ledger: see schema/feedback. Keep adverse facts; never relabel to pass.

  Parameters:

  • payload (required) — object — Evidence pack and decision context to test for missing proof.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• mvr_context_compile read-only

  Use after evidence capture to separate safe from unsafe inferences across formal, field, market, trust, and stakeholder context. It compiles context; it does not authorize action. Use when: Use when evidence is mixed and the agent needs safe claims versus unsafe claims before a verdict. Do not use when: Do not use as a go/no-go decision. Submit only consented, data-minimized, redacted or aggregated evidence; never raw confidential datasets, secrets, credentials, or personal identifiers. Evidence input location: arguments.payload. evidence_pack: object array. String fields: evidence_type, source_class, stakeholder_class, verification_status, source_date, source_doc_id. geography: string/object; evidence_geography: object; district: nonblank string; districts: nonblank strings array. source_date/freshness_date: YYYY, YYYY-MM, YYYY-MM-DD or ISO timestamp with timezone. source_date_range: {earliest,latest}, same-precision ordered bounds within supplied dates. analysis_date stays exact. Intervals have age_days:null and age_days_min/max; unresolved window/future overlap excludes coverage. Omit unknown dates/references, never null or invented. verification_status: unverified if unchecked. *_role: original_source_record, independent_evaluation or human_attestation; else ARTIFACT_ROLE_NOT_SOURCE_EVIDENCE. collection_context + provenance_ledger: see schema/feedback. Keep adverse facts; never relabel to pass.

  Parameters:

  • payload (required) — object — Resolved subject, market scope, and mixed evidence to compile into safe and unsafe inferences.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• mvr_decision_check read-only

  Use after evidence completeness to route a structurally complete pack toward licensed MVR scoring or abstain on missing proof. This public tool does not compute market, pilot, or scale readiness. Use when: Use after evidence completeness to determine whether the pack can be routed to licensed MVR scoring or still requires proof. Do not use when: Do not use as readiness, pilot, credit, legal, regulatory, or scale authorization. Submit only consented, data-minimized, redacted or aggregated evidence; never secrets, credentials, or personal identifiers. Evidence input location: arguments.payload. evidence_pack: object array. String fields: evidence_type, source_class, stakeholder_class, verification_status, source_date, source_doc_id. geography: string/object; evidence_geography: object; district: nonblank string; districts: nonblank strings array. source_date/freshness_date: YYYY, YYYY-MM, YYYY-MM-DD or ISO timestamp with timezone. source_date_range: {earliest,latest}, same-precision ordered bounds within supplied dates. analysis_date stays exact. Intervals have age_days:null and age_days_min/max; unresolved window/future overlap excludes coverage. Omit unknown dates/references, never null or invented. verification_status: unverified if unchecked. *_role: original_source_record, independent_evaluation or human_attestation; else ARTIFACT_ROLE_NOT_SOURCE_EVIDENCE. collection_context + provenance_ledger: see schema/feedback. Keep adverse facts; never relabel to pass.

  Parameters:

  • payload (required) — object — Decision question, resolved subject, market scope, and evidence for a bounded recommendation or abstention.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.