Public tool manifest · v2.24.0

Know every tool before connecting.

Every model-callable research and memory operation has its own named tool, strict input schema, and annotations. Open AI mode explores new trader-owned architectures without PrimeSync.me presets; Preserve mode protects supplied logic during repairs and conversions. Research tools return code and analysis with a metadata-only audit event. Separate memory tools distinguish reading, saving and erasing explicitly approved preferences and project summaries. No tool can publish code, contact a broker, or place a trade.

Machine-readable manifesthttps://ai.primesync.me/api/tool-manifest

What you can build

Build strategies
Turn your trading rules into candidate Pine Script or Python code.
Create indicators
Build custom chart indicators using the logic you choose.
Add alerts
Request alert code, then create, activate and test your alerts in TradingView.
Fix or convert code
Repair scripts or convert indicators and strategies, with changes limited to what you approve.
Set strategy Properties
Choose P0–P4 or Custom for account size, position sizing, costs and execution.
Check your code
Review logic, repainting, timing, sizing and costs through static code checks.
Research improvements
Turn supplied research into ideas and controlled experiments for your strategy.
Analyze backtests
Review TradingView or Python trade exports across your chosen assets and timeframes.
Run Monte Carlo tests
Explore possible drawdowns, losing streaks and uncertainty using your trade results.
Continue a project
Resume with a project summary or optional saved preferences and strategy summaries.

See the alert setup guide for what to request from Studio and what to configure in TradingView.

Access and counting

Build, audit, research analysis and Monte Carlo require an active Studio subscription and share 50 analysis jobs per calendar month. CSV imports and optional memory operations do not consume analysis jobs. See the complete counting rules.

Exact MCP tools

Compute-only result + metadata audit entry

Analyze supplied backtests

primesync_analyze_backtests

Permissions: strategies:build · strategies:validate
Reads: Only the goal, code, visual reference, client-supplied strategy ID and research ledger, and TradingView CSV data supplied in the current tool call.
Returns: Analyze supplied closed-trade datasets and report historical metrics, seeded robustness results, and evidence gaps. Does not optimize entry filters.
External effects: Writes one metadata-only audit event (tool, scopes, client, time, status). It does not save code, execute submitted code, call brokers, publish scripts, or access TradingView accounts.

Compute-only result + metadata audit entry

Bootstrap supplied backtests

primesync_bootstrap_backtests

Permissions: strategies:build · strategies:validate
Reads: Only the goal, code, visual reference, client-supplied strategy ID and research ledger, and TradingView CSV data supplied in the current tool call.
Returns: Run seeded bootstrap robustness analysis on supplied closed-trade CSV datasets. For return arrays or final candidate selection use primesync_monte_carlo.
External effects: Writes one metadata-only audit event (tool, scopes, client, time, status). It does not save code, execute submitted code, call brokers, publish scripts, or access TradingView accounts.

Compute-only result + metadata audit entry

Research entry-filter improvements

primesync_optimize_entry_filters

Permissions: strategies:build · strategies:validate
Reads: Only the goal, code, visual reference, client-supplied strategy ID and research ledger, and TradingView CSV data supplied in the current tool call.
Returns: Evaluate permitted entry-feature filters against a supplied baseline, chronological folds and holdout. Returns experimental candidates, never a guaranteed improvement.
External effects: Writes one metadata-only audit event (tool, scopes, client, time, status). It does not save code, execute submitted code, call brokers, publish scripts, or access TradingView accounts.

Compute-only result + metadata audit entry

Compare filters across assets

primesync_compare_asset_filters

Permissions: strategies:build · strategies:validate
Reads: Only the goal, code, visual reference, client-supplied strategy ID and research ledger, and TradingView CSV data supplied in the current tool call.
Returns: Evaluate common permitted entry-feature filters across supplied asset/timeframe datasets. Reports weak datasets and cross-asset robustness limits.
External effects: Writes one metadata-only audit event (tool, scopes, client, time, status). It does not save code, execute submitted code, call brokers, publish scripts, or access TradingView accounts.

Compute-only result + metadata audit entry

Design a research experiment

primesync_design_research_experiment

Permissions: strategies:build · strategies:validate
Reads: Only the goal, code, visual reference, client-supplied strategy ID and research ledger, and TradingView CSV data supplied in the current tool call.
Returns: Profile a research question and turn supplied academic evidence into isolated, source-linked hypotheses and candidate experiments requiring trader approval. Does not retrieve papers.
External effects: Writes one metadata-only audit event (tool, scopes, client, time, status). It does not save code, execute submitted code, call brokers, publish scripts, or access TradingView accounts.

Compute-only result + metadata audit entry

Design a strategy candidate

primesync_design_strategy_candidate

Permissions: strategies:build · strategies:validate
Reads: Only the goal, code, visual reference, client-supplied strategy ID and research ledger, and TradingView CSV data supplied in the current tool call.
Returns: Prepare a strategy candidate from trader-owned rules, supplied research evidence and approved change scope. Returns missing rules or a candidate/authoring handoff; does not execute strategy code.
External effects: Writes one metadata-only audit event (tool, scopes, client, time, status). It does not save code, execute submitted code, call brokers, publish scripts, or access TradingView accounts.

Compute-only result + metadata audit entry

Design an indicator candidate

primesync_design_indicator_candidate

Permissions: strategies:build · strategies:validate
Reads: Only the goal, code, visual reference, client-supplied strategy ID and research ledger, and TradingView CSV data supplied in the current tool call.
Returns: Prepare an indicator candidate from supplied rules and evidence. Returns a candidate/authoring handoff and any missing requirements; does not execute code.
External effects: Writes one metadata-only audit event (tool, scopes, client, time, status). It does not save code, execute submitted code, call brokers, publish scripts, or access TradingView accounts.

Compute-only result + metadata audit entry

Convert an indicator to a strategy

primesync_convert_indicator_to_strategy

Permissions: strategies:build · strategies:validate
Reads: Only the goal, code, visual reference, client-supplied strategy ID and research ledger, and TradingView CSV data supplied in the current tool call.
Returns: Prepare an indicator-to-strategy conversion from supplied base code, preserving the explicitly protected logic and visuals. Returns candidate or authoring guidance and parity checks.
External effects: Writes one metadata-only audit event (tool, scopes, client, time, status). It does not save code, execute submitted code, call brokers, publish scripts, or access TradingView accounts.

Compute-only result + metadata audit entry

Convert a strategy to an indicator

primesync_convert_strategy_to_indicator

Permissions: strategies:build · strategies:validate
Reads: Only the goal, code, visual reference, client-supplied strategy ID and research ledger, and TradingView CSV data supplied in the current tool call.
Returns: Prepare a strategy-to-indicator conversion from supplied base code with the requested preservation constraints. Returns candidate or authoring guidance and parity checks.
External effects: Writes one metadata-only audit event (tool, scopes, client, time, status). It does not save code, execute submitted code, call brokers, publish scripts, or access TradingView accounts.

Compute-only result + metadata audit entry

Validate code against backtest evidence

primesync_validate_code_evidence

Permissions: strategies:build · strategies:validate
Reads: Only the goal, code, visual reference, client-supplied strategy ID and research ledger, and TradingView CSV data supplied in the current tool call.
Returns: Evaluate supplied candidate code and fresh closed-trade exports with lineage, fold and robustness checks. Reports missing evidence; does not compile or execute code.
External effects: Writes one metadata-only audit event (tool, scopes, client, time, status). It does not save code, execute submitted code, call brokers, publish scripts, or access TradingView accounts.

Compute-only result + metadata audit entry

Backtest Importer

primesync_import_backtest

Permissions: strategies:validate
Reads: One supplied TradingView List of Trades CSV or Python closed-trade CSV plus explicit platform, asset, timeframe, timezone, and mapping metadata.
Returns: Dataset audit, normalized chronological returns, a dataset fingerprint, candidate/code-version/content-hash mapping, blueprint lineage, an explicit evidenceStatus, staged warnings, and the next action. BACKTEST EVIDENCE ACCEPTED requires matching blueprint hashes, a clean static pass, user-reported compilation, a user-attested fresh export, confirmed costs, matching confirmed effective Properties, and confirmed clean mapping; final selection additionally requires complete reproducibility metadata and comparable realistic Properties. P0/P4 remain comparison-only.
External effects: Writes one metadata-only audit event. It does not contact TradingView, save the CSV, or execute strategy code.

Compute-only result + metadata audit entry

Strategy Builder

primesync_strategy_builder

Permissions: strategies:build
Reads: The trader's idea, rules, market, timeframe, execution assumptions, costs, requested Pine/Python output, and any connected-AI code candidate returned for audit.
Returns: A top-of-response Strategy Completion Map followed by a bundled clarification, deterministic Pine candidate, or open connected-AI authoring contract for arbitrary complete Pine/Python architectures. Returned candidates receive blueprint-integrity and static audit findings.
External effects: Writes one metadata-only audit event. It does not place trades, save workspaces, or alter external files.

Compute-only result + metadata audit entry

Static Code Audit

primesync_audit_strategy

Permissions: strategies:audit
Reads: The approved rule blueprint, its required Strategy Builder hash, and supplied Pine Script or Python code.
Returns: A staged STATIC PASS, STATIC REVIEW REQUIRED, or STATIC FAILED result plus a stable code-content fingerprint and visible findings for blueprint drift, higher-timeframe leakage, look-ahead, negative offsets, pivots, intrabar execution, risk sizing, partial exits, stop mutation, sessions, pyramiding, alert/arrow parity, costs, direction, and rule coverage. Compilation and runtime behavior remain explicitly unconfirmed.
External effects: Writes one metadata-only audit event. It analyzes text and returns corrections in the conversation without changing external files.

Compute-only result + metadata audit entry

Monte Carlo

primesync_monte_carlo

Permissions: strategies:validate
Reads: Up to 20,000 chronological returns per candidate, original row counts, return unit, up to 100,000 simulations, comparison objective, optional account failure threshold, and caller-supplied compilation/export/cost/mapping lineage.
Returns: A standalone analytical result, backward-compatible provisional comparison, or fully gated final-candidate decision. Final mode requires complete fold, holdout, cost-stress, parameter-sensitivity, code-content, dataset, and parameter lineage; it reports reproducible percentiles, drawdown, losing-streak distribution, negative-result and optional failure-threshold probabilities, rejection reasons, and the exact unchanged preferred code.
External effects: Writes one metadata-only audit event. It does not build code, fetch market data, or execute trades.

Account-owned memory read + metadata audit entry

Read saved preferences

primesync_get_preferences

Permissions: memory:manage
Reads: Only this authenticated user's confirmed preferences and explicitly saved project summaries. Shared reviewer accounts are excluded.
Returns: Read whether optional memory is enabled and the current confirmed preferences and profileVersion.
External effects: Reads only owned memory; writes a metadata audit event. No memory changes.

Explicitly authorized memory change + metadata audit entry

Enable optional memory

primesync_enable_memory

Permissions: memory:manage
Reads: Only this authenticated user's confirmed preferences and explicitly saved project summaries. Shared reviewer accounts are excluded.
Returns: Enable memory only after explicit user consent; optionally save the supplied confirmed preferences.
External effects: Enable memory only after explicit user consent; optionally save the supplied confirmed preferences.

Explicitly authorized memory change + metadata audit entry

Update saved preferences

primesync_update_preferences

Permissions: memory:manage
Reads: Only this authenticated user's confirmed preferences and explicitly saved project summaries. Shared reviewer accounts are excluded.
Returns: Update or remove only the preferences explicitly requested by the user using the current profileVersion.
External effects: Update or remove only the preferences explicitly requested by the user using the current profileVersion.

Explicitly authorized memory change + metadata audit entry

Reset saved preferences

primesync_reset_preferences

Permissions: memory:manage
Reads: Only this authenticated user's confirmed preferences and explicitly saved project summaries. Shared reviewer accounts are excluded.
Returns: Erase all saved preferences after explicit consent using the current profileVersion. Keeps project summaries.
External effects: Erase all saved preferences after explicit consent using the current profileVersion. Keeps project summaries.

Explicitly authorized memory change + metadata audit entry

Disable and erase memory

primesync_disable_memory

Permissions: memory:manage
Reads: Only this authenticated user's confirmed preferences and explicitly saved project summaries. Shared reviewer accounts are excluded.
Returns: Disable optional memory and erase all saved preferences and project summaries after explicit consent. Does not erase exported copies or security logs.
External effects: Disable optional memory and erase all saved preferences and project summaries after explicit consent. Does not erase exported copies or security logs.

Explicitly authorized memory change + metadata audit entry

Delete all saved memory

primesync_delete_all_memory

Permissions: memory:manage
Reads: Only this authenticated user's confirmed preferences and explicitly saved project summaries. Shared reviewer accounts are excluded.
Returns: Erase all saved preferences and project summaries and leave memory off, after explicit consent. Does not erase exported copies or security logs.
External effects: Erase all saved preferences and project summaries and leave memory off, after explicit consent. Does not erase exported copies or security logs.

Account-owned memory read + metadata audit entry

Export saved memory

primesync_export_memory

Permissions: memory:manage
Reads: Only this authenticated user's confirmed preferences and explicitly saved project summaries. Shared reviewer accounts are excluded.
Returns: Read all confirmed preferences and project summaries as a portable export; does not write or delete memory.
External effects: Reads only owned memory; writes a metadata audit event. No memory changes.

Explicitly authorized memory change + metadata audit entry

Create a project summary

primesync_create_project_summary

Permissions: memory:manage
Reads: Only this authenticated user's confirmed preferences and explicitly saved project summaries. Shared reviewer accounts are excluded.
Returns: Create a new account-owned minimal project summary after explicit consent using the current profileVersion. Never store raw code or CSVs.
External effects: Create a new account-owned minimal project summary after explicit consent using the current profileVersion. Never store raw code or CSVs.

Explicitly authorized memory change + metadata audit entry

Update a project summary

primesync_update_project_summary

Permissions: memory:manage
Reads: Only this authenticated user's confirmed preferences and explicitly saved project summaries. Shared reviewer accounts are excluded.
Returns: Replace an owned project summary after explicit consent, matching its projectId, projectRevision and current profileVersion.
External effects: Replace an owned project summary after explicit consent, matching its projectId, projectRevision and current profileVersion.

Account-owned memory read + metadata audit entry

Read a project summary

primesync_get_project_summary

Permissions: memory:manage
Reads: Only this authenticated user's confirmed preferences and explicitly saved project summaries. Shared reviewer accounts are excluded.
Returns: Read one account-owned project summary by its projectId. Remembered evidence is user-reported, not reverified.
External effects: Reads only owned memory; writes a metadata audit event. No memory changes.

Account-owned memory read + metadata audit entry

List saved project summaries

primesync_list_project_summaries

Permissions: memory:manage
Reads: Only this authenticated user's confirmed preferences and explicitly saved project summaries. Shared reviewer accounts are excluded.
Returns: Read this account’s saved project summaries and portable request context. Does not save changes.
External effects: Reads only owned memory; writes a metadata audit event. No memory changes.

Explicitly authorized memory change + metadata audit entry

Delete a project summary

primesync_delete_project_summary

Permissions: memory:manage
Reads: Only this authenticated user's confirmed preferences and explicitly saved project summaries. Shared reviewer accounts are excluded.
Returns: Delete one owned project summary after explicit consent and matching profileVersion, projectId and projectRevision. Other projects remain.
External effects: Delete one owned project summary after explicit consent and matching profileVersion, projectId and projectRevision. Other projects remain.

Account-owned memory read + metadata audit entry

Read context for continuing a project

primesync_resume_project_summary

Permissions: memory:manage
Reads: Only this authenticated user's confirmed preferences and explicitly saved project summaries. Shared reviewer accounts are excluded.
Returns: Read a selected project’s context and next step; asks which project if selection is ambiguous. Does not execute or modify the project.
External effects: Reads only owned memory; writes a metadata audit event. No memory changes.

Typed result contracts

Every MCP tool publishes an outputSchema. The machine-readable manifest includes the complete JSON Schema definitions and example result objects so clients can parse imports, blueprints, drift checks, research ledgers, and Monte Carlo metrics without guessing.

primesync_import_backtestRequired: answer · status · evidenceStatus · dataset · chronologicalTradeReturns · chronologicalNetPnl · tradeIds · normalization · validationStages · lineage · verificationWarnings · traceabilityWarnings · nextAction

primesync_strategy_builderRequired: answer · status · blueprintHash · completionChecklist · sourceOfTradingRules · hiddenDefaults

primesync_audit_strategyRequired: answer · status · verificationStage · compileStatus · backtestStatus · robustnessStatus · approvedBlueprintHash · codeBlueprintHash · codeContentHash · blueprintDrift · counts · findings

primesync_monte_carloRequired: answer · status · finishedResult · method · randomSeed · selectionObjective · workflowMode · finalityStatus · evidenceProvenance · preferredCandidate · preferredCode · preferredCodeContentHash · rejectedCandidates · candidateResults · historical · simulated · codeChangeRule

primesync_analyze_backtestsRequired: answer · status · operatingMode · taskMode · objective · strategyCompletionMap · strategyProfile · researchQueries · callerAttestedSources · verifiedSources · independentSourceVerification · sourceVerificationBoundary · rejectedSources · sourceRelevanceScores · hypotheses · candidateExperiments · protectedLogic · missingEvidence · validationPlan · overfittingWarnings · researchStatus · nextAction · validationProcess · researchLedger

primesync_bootstrap_backtestsRequired: answer · status · operatingMode · taskMode · objective · strategyCompletionMap · strategyProfile · researchQueries · callerAttestedSources · verifiedSources · independentSourceVerification · sourceVerificationBoundary · rejectedSources · sourceRelevanceScores · hypotheses · candidateExperiments · protectedLogic · missingEvidence · validationPlan · overfittingWarnings · researchStatus · nextAction · validationProcess · researchLedger

primesync_optimize_entry_filtersRequired: answer · status · operatingMode · taskMode · objective · strategyCompletionMap · strategyProfile · researchQueries · callerAttestedSources · verifiedSources · independentSourceVerification · sourceVerificationBoundary · rejectedSources · sourceRelevanceScores · hypotheses · candidateExperiments · protectedLogic · missingEvidence · validationPlan · overfittingWarnings · researchStatus · nextAction · validationProcess · researchLedger

primesync_compare_asset_filtersRequired: answer · status · operatingMode · taskMode · objective · strategyCompletionMap · strategyProfile · researchQueries · callerAttestedSources · verifiedSources · independentSourceVerification · sourceVerificationBoundary · rejectedSources · sourceRelevanceScores · hypotheses · candidateExperiments · protectedLogic · missingEvidence · validationPlan · overfittingWarnings · researchStatus · nextAction · validationProcess · researchLedger

primesync_design_research_experimentRequired: answer · status · operatingMode · taskMode · objective · strategyCompletionMap · strategyProfile · researchQueries · callerAttestedSources · verifiedSources · independentSourceVerification · sourceVerificationBoundary · rejectedSources · sourceRelevanceScores · hypotheses · candidateExperiments · protectedLogic · missingEvidence · validationPlan · overfittingWarnings · researchStatus · nextAction · validationProcess · researchLedger

primesync_design_strategy_candidateRequired: answer · status · operatingMode · taskMode · objective · strategyCompletionMap · strategyProfile · researchQueries · callerAttestedSources · verifiedSources · independentSourceVerification · sourceVerificationBoundary · rejectedSources · sourceRelevanceScores · hypotheses · candidateExperiments · protectedLogic · missingEvidence · validationPlan · overfittingWarnings · researchStatus · nextAction · validationProcess · researchLedger

primesync_design_indicator_candidateRequired: answer · status · operatingMode · taskMode · objective · strategyCompletionMap · strategyProfile · researchQueries · callerAttestedSources · verifiedSources · independentSourceVerification · sourceVerificationBoundary · rejectedSources · sourceRelevanceScores · hypotheses · candidateExperiments · protectedLogic · missingEvidence · validationPlan · overfittingWarnings · researchStatus · nextAction · validationProcess · researchLedger

primesync_convert_indicator_to_strategyRequired: answer · status · operatingMode · taskMode · objective · strategyCompletionMap · strategyProfile · researchQueries · callerAttestedSources · verifiedSources · independentSourceVerification · sourceVerificationBoundary · rejectedSources · sourceRelevanceScores · hypotheses · candidateExperiments · protectedLogic · missingEvidence · validationPlan · overfittingWarnings · researchStatus · nextAction · validationProcess · researchLedger

primesync_convert_strategy_to_indicatorRequired: answer · status · operatingMode · taskMode · objective · strategyCompletionMap · strategyProfile · researchQueries · callerAttestedSources · verifiedSources · independentSourceVerification · sourceVerificationBoundary · rejectedSources · sourceRelevanceScores · hypotheses · candidateExperiments · protectedLogic · missingEvidence · validationPlan · overfittingWarnings · researchStatus · nextAction · validationProcess · researchLedger

primesync_validate_code_evidenceRequired: answer · status · operatingMode · taskMode · objective · strategyCompletionMap · strategyProfile · researchQueries · callerAttestedSources · verifiedSources · independentSourceVerification · sourceVerificationBoundary · rejectedSources · sourceRelevanceScores · hypotheses · candidateExperiments · protectedLogic · missingEvidence · validationPlan · overfittingWarnings · researchStatus · nextAction · validationProcess · researchLedger

primesync_get_preferencesRequired: status

primesync_enable_memoryRequired: status

primesync_update_preferencesRequired: status

primesync_reset_preferencesRequired: status

primesync_disable_memoryRequired: status

primesync_delete_all_memoryRequired: status

primesync_export_memoryRequired: status

primesync_create_project_summaryRequired: status

primesync_update_project_summaryRequired: status

primesync_get_project_summaryRequired: status

primesync_list_project_summariesRequired: status

primesync_delete_project_summaryRequired: status

primesync_resume_project_summaryRequired: status

Continuity is client-managed

strategyId and researchLedger carry the approved baseline, experiment history, accepted or rejected decisions, evidence, and blocked repeat suggestions. They are returned to your MCP client but are not stored by PrimeSync. The client must send the complete current ledger again on each relevant research call. Without it, only an explicitly selected saved summary can provide remembered decisions. Optional memory keeps minimal summaries and rejected-experiment notes, not the full research ledger or code. Recalled evidence never replaces fresh validation.