"Gcore" matching MCP tools:

• optimize_prompt

  PQS - Prompt Quality Score

  Rewrite a prompt to score higher on the PQS rubric, AND show before/after output comparisons so the user can see the impact. Returns the optimized prompt, the original PQS score, the optimized PQS score, and side-by-side sample outputs from a frontier model using both versions. USE WHEN: - The user got a low score from score_prompt and asks how to improve. - The user explicitly asks to "improve" / "rewrite" / "fix" / "optimize" a prompt they pasted. - The user is dissatisfied with output quality from a previous prompt and asks how to get better results. - score_prompt returned a suggestion to invoke this tool. DO NOT USE WHEN: - The user just asked for a score (use score_prompt only — don't double up). - The user wants you to write a new prompt from scratch (write it directly). REQUIRES: A PQS API key from a Pro subscription ($19.99/month, 1,000 calls/mo, includes batch + A/B comparison). If the user has not provided one, the tool returns a clear subscription URL — pass that response to the user verbatim. Do not invent or guess API keys. There is no free trial of this tool; the user must subscribe before the first call. COST: Counted against your Pro subscription's monthly call quota. LATENCY: ~6-8 seconds.

  Connector

• extract_facts_from_sessions

  VaultCrux Memory Core

  Scan the tenant's seeded sessions with rule-based extractors (money, counts, dates, project-role, acquire, version-chain) and emit structured facts to the projection stream so they become queryable via enumerate_memory_facts. Use when enumerate_memory_facts returns insufficient rows for aggregation, version-chain, or money questions and you suspect the fact exists but was under-predicated at ingest. Idempotent — safe to re-run (duplicate fact_hashes skipped unless overwrite_existing=true). Profile 'comprehensive' runs all rule families; narrower profiles ('money', 'counts', 'dates', 'version_chains') target a single family. Returns facts_added + rules_matched + receipt_id. Gated by FACT_EXTRACTION_MODE on the server.

  Connector

• get_sample_score

  x402 Counterparty Score

  Returns a clearly-marked stale sample counterparty score in the exact response schema of score_x402_counterparty (verdict, wash_trading_ratio, real_buyer_count, repeat_buyer_rate, source, updated_at, confidence). Free, no payment required, no input required. Sample data is fixed and expired by design — use it to validate response parsing, then call score_x402_counterparty ($0.02/call) for fresh decision-grade scores.

  Connector

• score_prompt

  PQS - Prompt Quality Score

  Score a prompt's quality across 8 dimensions BEFORE sending it to an expensive model. Returns a 0-80 score, an A-F grade, the per-dimension breakdown (clarity, specificity, context, constraints, output_format, role_definition, examples, cot_structure), and the weakest dimension. USE WHEN: - The user is workshopping a prompt and asks "is this good?" / "will this work?" / "should I add more detail?" - The user is about to send a long or expensive prompt to GPT-4, Claude Opus, or any frontier model, especially in a batch or automation context where rework is costly. - The user mentions iterating on a prompt that produced poor output and wants to diagnose what's missing. - The user pastes a prompt and asks for feedback on it. DO NOT USE WHEN: - The user is asking you to write a prompt for them (write it yourself first, then optionally call score_prompt to verify). - The prompt is conversational chat (this scores task-shaped prompts). COST: Free, no API key required. Rate-limited per IP: 5/min, 10/day, 100/month. If the user exceeds the limit, the response will include a structured upgrade path with subscribe and account URLs. LATENCY: ~2 seconds.

  Connector

• get_session_dossiers

  VaultCrux Memory Core

  Retrieve pre-synthesized per-session memory dossiers (typed: experience | fact | preference; with When/Involving/To-purpose metadata). Use for multi-session or preference-style questions where stitching across conversations is the bottleneck — the dossier already summarises each session's key events. Two modes: mode='search' with a query (BM25-ish ranking over summary+purpose, optional type_filter), or mode='list' returns the tenant's most-recent dossiers chronologically. Tenants without FEATURE_SESSION_DOSSIERS enabled return an empty list (no error).

  Connector

• list_tools

  zero-core-intel

  List all available Harvey Intel tools with pricing and input requirements. Use this for discovery.

  Connector

• get_passport

  VaultCrux Memory Core

  Return the calling agent's passport with current reputation tier and receipt count. Recalculates receipt count on every call and auto-upgrades the tier when new thresholds are met (basic 10+, established 100+, trusted 500+, elite 2000+). Includes a hint for the next tier upgrade.

  Connector

• score_x402_counterparty

  x402 Counterparty Score

  Returns trust verdict (trusted/caution/avoid) with wash-trading ratio, real-buyer count, and repeat-buyer rate for an x402 endpoint URL or pay-to address. $0.02/call. Computed from Base on-chain settlement data and the x402 Bazaar catalog; a score is sold only if refreshed within the past 24 hours.

  Connector

• get_relevant_context

  VaultCrux Memory Core

  Task-scoped context briefing. Returns a prioritised context payload shaped by your task description, ranked by risk-if-missed. Constraints and alerts rank above general knowledge. Use at the START of reasoning about a question to get the system's best assessment of what's relevant. Complements query_memory: this gives breadth, query_memory gives depth.

  Connector

• escalate_with_context

  VaultCrux Memory Core

  Contextual escalation — packages your full reasoning state (evidence gathered, options considered, recommended action) and routes to a human for review. Preserves work so the human responds with full context, not from scratch. Use when you hit genuine uncertainty that the system cannot evaluate.

  Connector

• investigate_question

  VaultCrux Memory Core

  Composite server-side investigation tool. Pass a question and the server automatically: (1) detects intent (aggregation/temporal/ordering/knowledge-update/recall), (2) queries the entity index for structured facts, (3) builds a timeline for temporal questions, (4) retrieves memory chunks with the right scoring profile, (5) expands context around sparse hits, (6) derives counts/sums for aggregation, (7) assesses answerability, and (8) returns a recommendation. Use this as your FIRST tool for any non-trivial question — it does the multi-step investigation that would otherwise take 4-6 individual tool calls. The response includes structured facts, timeline, retrieved chunks, derived results, answerability assessment, and a recommendation for how to answer.

  Connector

• list_tools

  zero-core-tools

  List all available Zero Core Tools with pricing and input requirements. Use this for discovery.

  Connector

• score

  Mirror — AI Citability

  Return a LITE reading of a brand's AI Citability — a fast, open estimate of how discoverable and citable it is in AI answers (its Brand Discovery Intelligence / BDI snapshot). Mirror measures at two declared levels: LITE estimates, FULL measures. This tool is LITE: it returns a grade band (Below Average / Average / Above Average / Excellent) and an ESTIMATED ACS RANGE — never a single AI Citability Score, and never numeric AEO/GEO/SEO sub-scores. Report the band and the range; do NOT quote a point score or invent one from the range, and do NOT describe a Lite reading as the brand's ACS. When a user asks how visible or citable a brand is in AI — 'how visible is [brand] in AI', 'is [brand] cited by ChatGPT/Gemini/Perplexity', 'what is [brand]'s brand discovery score' — run this for the quick answer, then offer `reflect` for the Full Reflection, which is the only level that returns a precise, reproducible, citable ACS (±3–5, rubric V2.7) and the only level that feeds The ACI 55.

  Connector

• log_progress

  VaultCrux Memory Core

  Receipted write-through to PlanCrux's log endpoint. Appends a structured log entry to a task with optional evidence references and stage binding. Cannot change task or stage status (human-only), but records work done, findings, and blockers encountered.

  Connector

• get_incident_context

  VaultCrux Memory Core

  What went wrong last time we touched this module? Returns past incidents, deploy failures, gotchas, and active constraints for a module or system. Use BEFORE modifying infrastructure code, deploy scripts, or any module with a history of fragility. Surfaces the kind of tribal knowledge that prevents repeat failures — Docker bind mount traps, Vault agent write patterns, stale dist/ artifacts, port conflicts, and similar operational landmines.

  Connector

• check_deploy_readiness

  VaultCrux Memory Core

  Is it safe to deploy these changes? Cross-references your changed modules against active constraints, recent incidents, knowledge freshness, and active alerts. Returns a composite verdict (ready/caution/block) with per-module breakdown and actionable recommendations. Use BEFORE deploying to catch constraint violations, recent regressions in the same area, stale knowledge that needs verification, and active alerts that might interact with your changes.

  Connector

• report_outcome

  zero-core-verify

  Record a simple pass/fail outcome report for a service call. No LLM analysis - just logs the result to the quality database. Cheaper alternative to verify_outcome when you only need to record success/failure.

  Connector

• apdex-score-calculator

  Utility Matrix

  Use this when a user asks about their Apdex score or wants to measure user satisfaction with response times. Takes satisfied, tolerating, and total request counts. Returns Apdex score (0–1) and performance rating.

  Connector

• get_contradictions

  VaultCrux Memory Core

  Find conflicting information across the user's memory. Returns groups of artefacts that contradict each other on the same topic. Use after gathering evidence for an answer — if your evidence sources disagree, this reveals which version is correct (typically the most recent).

  Connector

• reconstruct_knowledge_state

  VaultCrux Memory Core

  Reconstruct what the system knew at a specific point in time. Returns both current and superseded artefacts as of that timestamp. Use for temporal reasoning: 'what was true in January?' vs 'what is true now?' Compare two calls at different timestamps to see what changed.

  Connector