Official MCP RegistryListed
Neotic
AI agents create contextual in-app experiences, announcements, and triggers with Neotic.
First seen 2 Oct 2026. Evidence as of 2 Oct 2026.
140
Tools
From an anonymous probe
1
Source listings
Each with its own history
0
Recorded changes
Since first seen
Tools
| Tool | Description | Behaviour |
|---|---|---|
| cognitive_allocate_compute | Adaptive compute budgeting: select compute tier (Fast Path to Deep Deliberation) and timeout based on EVC. | Not declared |
| cognitive_analogical_transfer | Transfer structural strategies across disparate domains via Structure-Mapping Engine (SME). | Not declared |
| cognitive_analyze_communication | Pragmatic communication: audit speech acts against Gricean maxims (Quality, Quantity, Relation, Manner) and detect deception. | Not declared |
| cognitive_arbitrate_temporal_objectives | Arbitrate short vs long term payoffs using hyperbolic vs exponential discounting and Ulysses pre-commitment contracts. | Not declared |
| cognitive_assess_competence | Epistemic boundary awareness: classify task into KNOWN, KNOWN_UNKNOWN, or UNKNOWN_UNKNOWN (OOD) and track calibration. | Not declared |
| cognitive_audit_evidence_graph | Audit the evidence graph for a task before issuing final answers. Rejects claims such as 'optimal', 'verified', or 'feasible' when their evidence dependencies are incomplete. | Not declared |
| cognitive_build_evidence_graph | Build or update an Evidence-Carrying Cognitive Graph for a task structure and solution trace. | Not declared |
| cognitive_causal_analysis | Distinguish causal effects (do-calculus) from spurious correlation via backdoor adjustment. | Not declared |
| cognitive_compile_invariant_lattice | Compile a Dynamic Constraint Lattice (DCL) into algebraic boundaries, conservation laws, and reachability cones. | Not declared |
| cognitive_compose_strategies | Skill Composition: synthesize a composite multi-stage StrategyIR from primitive strategies. Chains multiple specialized skills (e.g. Graph Coloring + Topological Sort + Allocation) into a compound pipeline with explicit stage transitions and end-to-end verification. | Not declared |
| cognitive_compute_intrinsic_rewards | Compute intrinsic drives: novelty & prediction surprise curiosity, empowerment (channel capacity), and learning progress. | Not declared |
| cognitive_compute_lattice_signature | Compute coordinate-free topological invariant signature of a lattice or task. | Not declared |
| cognitive_compute_number_theory | Number theory: primality, factoring, extended GCD, Diophantine, modular inverse, CRT, combinatorics, Fibonacci. | Not declared |
| cognitive_counterfactual_what_if | Counterfactual engine: evaluate 'What if I had done X instead of Y at step t?' using Pearl's abduction-intervention-prediction. | Not declared |
| cognitive_create_simulated_environment | Instantiate and initialize a simulated cognitive environment (spatial_commons, multi_agent_arena, sequential_puzzle). | Not declared |
| cognitive_crucible_stress_test | Subject candidate trajectories to adversarial algebraic perturbations to calculate Robustness Index (R) and project hardened paths. | Not declared |
| cognitive_evaluate_claim_evidence | Evaluate support status and confidence for an individual claim with evidence. | Not declared |
| cognitive_evaluate_cooperation | Multi-agent cooperation: analyze game payoff matrices, compute Nash/Pareto equilibria, and execute reciprocity policies. | Not declared |
| cognitive_evaluate_counterfactual_query | Evaluate a counterfactual query on a plan ('What if capacity drops?', 'What if a route fails?', etc.). | Not declared |
| cognitive_evaluate_generalization_benchmarks | Evaluate broad generalization across spatial commons, multi-agent arenas, and sequential causal puzzles. | Not declared |
| cognitive_execute_task | One-call orchestration: identify → gate → guide → solve → verify → report. Parameters: - task: Dict containing: - task_structure (or loose definition: name, entities, constraints, etc.) - raw (optional): Domain-specific execution payload. If omitted, returns status='guidance_only' with 'recommended_action'='supply_raw' and an 'expected_raw_formats' object detailing valid schemas. Supported problem types for task.raw: * scheduling: {"workers": [{"id": "w1", "eligible_shifts": ["s1"], "max_shifts": 1}], "shifts": [{"id": "s1", "required_workers": 1}]} * allocation: {"consumers": [{"id": "c1", "demands": {"r1": 1}}], "resources": [{"id": "r1", "capacity": 2}]} * graph: {"nodes": ["A", "B"], "edges": [["A", "B"]]} * graph_coloring: {"nodes": ["A", "B"], "edges": [["A", "B"]], "colors": ["red", "blue"]} * shortest_path: {"nodes": ["A", "B"], "edges": [["A", "B"]], "weights": {"A->B": 1.0}, "start": "A", "target": "B"} * math: {"math": {"question": "...", "quantities": {...}, "equations": [...], "target_variable": "x", "ground_truth": 42.0}} * code: {"code": {"code": "def solution()...", "tests": ["assert ..."]}} * pddl: {"pddl": {"plan": [...], "init": {...}, "goal": {...}}} Returns a single envelope with status (completed / guidance_only / blocked_until_clarified / no_applicable_guidance / refused_infeasible / failed), solution, score, assumptions, failure reasons, and expected_raw_formats. | Not declared |
| cognitive_few_shot_induce | Few-shot learning: induce a generalized procedural StrategyIR from 1-3 problem traces. Extracts structural invariants (decision ordering, invariant contracts, verification rules) and registers an initial candidate strategy immediately without requiring large training sets. | Not declared |
| cognitive_generate_and_prioritize_goals | Autonomous goal synthesis from world deficits, depleted reserves, and exploration frontiers with multi-criteria prioritization. | Not declared |
| cognitive_get_experiment | Retrieve details and benchmark results of an experiment (§24, §69). | Not declared |
| cognitive_get_final_evidence_result | Compile a final evidence result listing supporting evidence, assumptions, missing evidence, contradictions, unchecked dependencies, confidence, and invalidation conditions. | Not declared |
| cognitive_get_guidance | Retrieve applicable validated strategies for a task (§24, §18). Does NOT return unverified or suspended strategies as trusted guidance. Provides calibrated uncertainty, applicability conditions, and negative transfer warnings. Args: task_structure_id: UUID of the abstract task structure. environment: Environment characteristics. goal: Goal description and metric targets. available_capabilities: Capabilities supported by the caller. model_family: Model family of the consumer agent (e.g. 'claude', 'gpt', 'local'). Returns: Ranked list of applicable strategies with procedures, conditions, and evidence. Failures return {"error", "detail", "hint"} — never a bare exception. | Not declared |
| cognitive_get_strategy | Retrieve a usable strategy: steps, when to use, when not, evidence summary. Disclosure: you learn WHAT to execute, never HOW the engine induces, verifies, or ranks knowledge (no trust signals, audit, tenants, traces). | Not declared |
| cognitive_get_strategy_report | Evidence dossier: baseline vs assisted, distribution, CI, failures, last eval. | Not declared |
| cognitive_ground_language | Non-LLM compositional semantics: parse utterance into semantic predicates and evaluate directly against WorldState. | Not declared |
| cognitive_hierarchical_plan | Decompose high-level goals into milestone subgoals using Hierarchical Task Network (HTN) planning. | Not declared |
| cognitive_identify_task | Create or resolve an abstract task structure without storing raw private content (§24). Args: task_structure: Structural representation (entities, constraints, variables, etc.). environment: Environmental context and characteristics. goal: Objective and optimization goals. Returns: task_structure_id, structural_features, and matching existing structures. On invalid input returns {"error", "detail", "hint"} instead of raising, so the MCP client sees the cause instead of a generic execution error. | Not declared |
| cognitive_induce_morphic_transfer | Discover topological homomorphism between source experience and target problem, transducing solution paths. | Not declared |
| cognitive_infer | Perform logical deduction (Horn clauses) or exact probabilistic Bayesian network inference. | Not declared |
| cognitive_infer_human_values | Infer human values via Bradley-Terry IRL, detect Goodhart's law / specification gaming, and assess CIRL deference. | Not declared |
| cognitive_inspect_lexicon | Inspect grounded lexicon acquired via situated interaction (learned vocabulary, concept bindings, confidence). | Not declared |
| cognitive_inspect_self_model | Engine self-model introspection: inspect capabilities, domain competence, active subsystems, and safety status. | Not declared |
| cognitive_learn_from_mistake | Online Real-Time Error Reflection & Strategy Patching. When an execution fails, analyzes root-cause constraint violations, synthesizes new exception cases and repair procedures, verifies update against anchor regression, and publishes the patched strategy version in real time. | Not declared |
| cognitive_learn_language_interaction | Interactive language acquisition: learn word-concept bindings through cross-situational observation, games, and feedback. | Not declared |
| cognitive_learn_world_model | Online world model learning: update state transition priors from empirical execution traces. | Not declared |
| cognitive_list_experiments | Discovery: list recorded benchmark experiment IDs for cognitive.get_experiment. | Not declared |
| cognitive_matrix_algebra | Exact rational matrix & vector algebra: multiply, determinant, inverse, transpose, trace, eigenvalues, dot/cross. | Not declared |
| cognitive_monitor_reasoning | Introspective reasoning critic: inspect trace in-flight to catch cycles, invariant drift, vacuous output, and stalling. | Not declared |
| cognitive_parse_task | Convert natural-language task text into CIR and task_structure dict. Every natural-language input is normalized into CIR before reasoning. Returns both the normalized CIR and a human-readable explanation. | Not declared |
| cognitive_plan_with_counterfactuals | Synthesize the best verified plan across candidate rollouts, uncertainty tracking, and constraint pruning. | Not declared |
| cognitive_predict_world_state | Forward world model: predict future state trajectories and uncertainty bounds under actions. | Not declared |
| cognitive_project_to_manifold | Project a candidate state or plan step onto the Singular Transition Manifold M = F(S0) ∩ B(Goal). Returns the corrected state, corrective delta vector Delta S = S* - S, and boundary distance margins. | Not declared |
| cognitive_propose_strategy | Propose a candidate strategy from problem-solving experience (§24, §2). IMPORTANT: This NEVER makes the strategy TRUSTED. The strategy enters CANDIDATE state and requires objective verification. | Not declared |
| cognitive_record_experience | Record an observable event in an ongoing experience episode (§24, §7). Accepts structured actions, observations, and state changes. Never sends raw unredacted private transcripts. | Not declared |
| cognitive_refine_lattice_from_feedback | Autonomously evolve higher-order invariants, tighten bounds, and discover cliques from execution feedback. | Not declared |
| cognitive_report_transfer | Record whether a transferred strategy helped or harmed on a novel task (§24, §19). | Not declared |
| cognitive_resolve_intent | Pragmatics: resolve indirect speech acts (e.g. ability questions to directives), anaphoric pronouns, and verify presuppositions. | Not declared |
| cognitive_run_closed_loop_agent | Run the end-to-end cognitive agent closed loop (Perceive -> Model -> Decide -> Act -> Reflect -> Learn). | Not declared |
| cognitive_run_multi_agent_simulation | Simulate repeated multi-agent interaction with social dilemmas, speech acts, and reputation tracking. | Not declared |
| cognitive_safe_self_improve | Safe self-improvement: propose modifications guarded by immutable verification oracles and anchor regressions. | Not declared |
| cognitive_simulate_actions | Simulate and rank candidate actions by predicted feasibility, reward, and constraint safety. | Not declared |
| cognitive_solve_and_compare | End-to-end autonomy: identify → guide → execute → baseline → verify → verdict. Give raw task data (scheduling: workers/shifts/eligibility/capacity/ exclusivity; graph: nodes/edges; allocation: consumers/resources/...). Returns the guided solution, the unguided baseline, independent verification of both (with objective_source + independently_verified), and whether the engine improved the result. | Not declared |
| cognitive_solve_arithmetic | Evaluate or simplify mathematical expressions (PEMDAS with power, functions like sqrt, exp, log, sin, cos). | Not declared |
| cognitive_solve_equation_system | Solve linear equations (ax + b = c), quadratic equations (ax^2 + bx + c = 0), or linear systems (A x = b). | Not declared |
| cognitive_solve_word_problem | Solve math word problems (GSM8K/SVAMP/MATH) via topological constraint propagation. | Not declared |
| cognitive_start_experience | Start an experience episode (§24, §10). Does not store raw prompts or full conversations. For long-horizon work, pass parent_experience_id (+ subgoal) to chain episodes with an inherited goal stack; unknown parents are rejected, never silently adopted. | Not declared |
| cognitive_step_simulated_environment | Step an active simulated environment with an agent action. | Not declared |
| cognitive_submit_outcome | Submit the structured outcome of an experience episode (§24, §10). Triggering this may induce candidate strategies in the engine. | Not declared |
| cognitive_synthesize_program | Synthesize new algorithmic Python procedures on the fly with AST sandboxing and verification. | Not declared |
| cognitive_synthesize_singular_path | Synthesize an optimal, invariant-verified trajectory from initial state to goal through the singular bottleneck. Eliminates dead-end branching and hallucinated unfeasible solutions. | Not declared |
| cognitive_theory_of_mind | Theory of Mind: model agents' BDI mental states, test false beliefs (Sally-Anne), and infer goals via inverse planning. | Not declared |
| cognitive_tree_search | Perform Monte Carlo Tree Search (UCT) over action sequences to find optimal trajectory. | Not declared |
| cognitive_verify_arithmetic_claim | Formally verify an arithmetic equality claim, audit numerical stability, condition number, and cancellation risks. | Not declared |
| cognitive_verify_ethics_and_norms | Normative ethics & fairness: enforce deontological vetos, evaluate Rawlsian vs Utilitarian welfare, and arbitrate moral dilemmas. | Not declared |
| cognitive_verify_lattice_transition | Verify a candidate state or transition S_t -> S_{t+1} against invariant boundary manifolds. | Not declared |
| cognitive_verify_strategy | Run objective deterministic verification on a strategy (§24, §16). Clients cannot self-promote. Verification is evaluated server-side. Pass task_structure_id (from cognitive.identify_task) so constraints are independently recomputed from registered descriptors instead of trusting trace flags. Objective precedence: explicit caller value → recomputed from raw data → registered spec (labeled unknown) → nested trace claims ONLY when trust_trace_objective=true → otherwise unknown, never silent 0.0. Returns passed/score plus details.objective_source and details.independently_verified so callers know what was recomputed versus taken on trace claims. Failures are structured, never bare. | Not declared |
| cognitive.allocate_compute | Adaptive compute budgeting: select compute tier (Fast Path to Deep Deliberation) and timeout based on EVC. | Not declared |
| cognitive.analogical_transfer | Transfer structural strategies across disparate domains via Structure-Mapping Engine (SME). | Not declared |
| cognitive.analyze_communication | Pragmatic communication: audit speech acts against Gricean maxims (Quality, Quantity, Relation, Manner) and detect deception. | Not declared |
| cognitive.arbitrate_temporal_objectives | Arbitrate short vs long term payoffs using hyperbolic vs exponential discounting and Ulysses pre-commitment contracts. | Not declared |
| cognitive.assess_competence | Epistemic boundary awareness: classify task into KNOWN, KNOWN_UNKNOWN, or UNKNOWN_UNKNOWN (OOD) and track calibration. | Not declared |
| cognitive.audit_evidence_graph | Audit the evidence graph for a task before issuing final answers. Rejects claims such as 'optimal', 'verified', or 'feasible' when their evidence dependencies are incomplete. | Not declared |
| cognitive.build_evidence_graph | Build or update an Evidence-Carrying Cognitive Graph for a task structure and solution trace. | Not declared |
| cognitive.causal_analysis | Distinguish causal effects (do-calculus) from spurious correlation via backdoor adjustment. | Not declared |
| cognitive.compile_invariant_lattice | Compile a Dynamic Constraint Lattice (DCL) into algebraic boundaries, conservation laws, and reachability cones. | Not declared |
| cognitive.compose_strategies | Skill Composition: synthesize a composite multi-stage StrategyIR from primitive strategies. Chains multiple specialized skills (e.g. Graph Coloring + Topological Sort + Allocation) into a compound pipeline with explicit stage transitions and end-to-end verification. | Not declared |
| cognitive.compute_intrinsic_rewards | Compute intrinsic drives: novelty & prediction surprise curiosity, empowerment (channel capacity), and learning progress. | Not declared |
| cognitive.compute_lattice_signature | Compute coordinate-free topological invariant signature of a lattice or task. | Not declared |
| cognitive.compute_number_theory | Number theory: primality, factoring, extended GCD, Diophantine, modular inverse, CRT, combinatorics, Fibonacci. | Not declared |
| cognitive.counterfactual_what_if | Counterfactual engine: evaluate 'What if I had done X instead of Y at step t?' using Pearl's abduction-intervention-prediction. | Not declared |
| cognitive.create_simulated_environment | Instantiate and initialize a simulated cognitive environment (spatial_commons, multi_agent_arena, sequential_puzzle). | Not declared |
| cognitive.crucible_stress_test | Subject candidate trajectories to adversarial algebraic perturbations to calculate Robustness Index (R) and project hardened paths. | Not declared |
| cognitive.evaluate_claim_evidence | Evaluate support status and confidence for an individual claim with evidence. | Not declared |
| cognitive.evaluate_cooperation | Multi-agent cooperation: analyze game payoff matrices, compute Nash/Pareto equilibria, and execute reciprocity policies. | Not declared |
| cognitive.evaluate_counterfactual_query | Evaluate a counterfactual query on a plan ('What if capacity drops?', 'What if a route fails?', etc.). | Not declared |
| cognitive.evaluate_generalization_benchmarks | Evaluate broad generalization across spatial commons, multi-agent arenas, and sequential causal puzzles. | Not declared |
| cognitive.execute_task | One-call orchestration: identify → gate → guide → solve → verify → report. Parameters: - task: Dict containing: - task_structure (or loose definition: name, entities, constraints, etc.) - raw (optional): Domain-specific execution payload. If omitted, returns status='guidance_only' with 'recommended_action'='supply_raw' and an 'expected_raw_formats' object detailing valid schemas. Supported problem types for task.raw: * scheduling: {"workers": [{"id": "w1", "eligible_shifts": ["s1"], "max_shifts": 1}], "shifts": [{"id": "s1", "required_workers": 1}]} * allocation: {"consumers": [{"id": "c1", "demands": {"r1": 1}}], "resources": [{"id": "r1", "capacity": 2}]} * graph: {"nodes": ["A", "B"], "edges": [["A", "B"]]} * graph_coloring: {"nodes": ["A", "B"], "edges": [["A", "B"]], "colors": ["red", "blue"]} * shortest_path: {"nodes": ["A", "B"], "edges": [["A", "B"]], "weights": {"A->B": 1.0}, "start": "A", "target": "B"} * math: {"math": {"question": "...", "quantities": {...}, "equations": [...], "target_variable": "x", "ground_truth": 42.0}} * code: {"code": {"code": "def solution()...", "tests": ["assert ..."]}} * pddl: {"pddl": {"plan": [...], "init": {...}, "goal": {...}}} Returns a single envelope with status (completed / guidance_only / blocked_until_clarified / no_applicable_guidance / refused_infeasible / failed), solution, score, assumptions, failure reasons, and expected_raw_formats. | Not declared |
| cognitive.few_shot_induce | Few-shot learning: induce a generalized procedural StrategyIR from 1-3 problem traces. Extracts structural invariants (decision ordering, invariant contracts, verification rules) and registers an initial candidate strategy immediately without requiring large training sets. | Not declared |
| cognitive.generate_and_prioritize_goals | Autonomous goal synthesis from world deficits, depleted reserves, and exploration frontiers with multi-criteria prioritization. | Not declared |
| cognitive.get_experiment | Retrieve details and benchmark results of an experiment (§24, §69). | Not declared |
| cognitive.get_final_evidence_result | Compile a final evidence result listing supporting evidence, assumptions, missing evidence, contradictions, unchecked dependencies, confidence, and invalidation conditions. | Not declared |
| cognitive.get_guidance | Retrieve applicable validated strategies for a task (§24, §18). Does NOT return unverified or suspended strategies as trusted guidance. Provides calibrated uncertainty, applicability conditions, and negative transfer warnings. Args: task_structure_id: UUID of the abstract task structure. environment: Environment characteristics. goal: Goal description and metric targets. available_capabilities: Capabilities supported by the caller. model_family: Model family of the consumer agent (e.g. 'claude', 'gpt', 'local'). Returns: Ranked list of applicable strategies with procedures, conditions, and evidence. Failures return {"error", "detail", "hint"} — never a bare exception. | Not declared |
| cognitive.get_strategy | Retrieve a usable strategy: steps, when to use, when not, evidence summary. Disclosure: you learn WHAT to execute, never HOW the engine induces, verifies, or ranks knowledge (no trust signals, audit, tenants, traces). | Not declared |
| cognitive.get_strategy_report | Evidence dossier: baseline vs assisted, distribution, CI, failures, last eval. | Not declared |
| cognitive.ground_language | Non-LLM compositional semantics: parse utterance into semantic predicates and evaluate directly against WorldState. | Not declared |
| cognitive.hierarchical_plan | Decompose high-level goals into milestone subgoals using Hierarchical Task Network (HTN) planning. | Not declared |
| cognitive.identify_task | Create or resolve an abstract task structure without storing raw private content (§24). Args: task_structure: Structural representation (entities, constraints, variables, etc.). environment: Environmental context and characteristics. goal: Objective and optimization goals. Returns: task_structure_id, structural_features, and matching existing structures. On invalid input returns {"error", "detail", "hint"} instead of raising, so the MCP client sees the cause instead of a generic execution error. | Not declared |
| cognitive.induce_morphic_transfer | Discover topological homomorphism between source experience and target problem, transducing solution paths. | Not declared |
| cognitive.infer | Perform logical deduction (Horn clauses) or exact probabilistic Bayesian network inference. | Not declared |
| cognitive.infer_human_values | Infer human values via Bradley-Terry IRL, detect Goodhart's law / specification gaming, and assess CIRL deference. | Not declared |
| cognitive.inspect_lexicon | Inspect grounded lexicon acquired via situated interaction (learned vocabulary, concept bindings, confidence). | Not declared |
| cognitive.inspect_self_model | Engine self-model introspection: inspect capabilities, domain competence, active subsystems, and safety status. | Not declared |
| cognitive.learn_from_mistake | Online Real-Time Error Reflection & Strategy Patching. When an execution fails, analyzes root-cause constraint violations, synthesizes new exception cases and repair procedures, verifies update against anchor regression, and publishes the patched strategy version in real time. | Not declared |
| cognitive.learn_language_interaction | Interactive language acquisition: learn word-concept bindings through cross-situational observation, games, and feedback. | Not declared |
| cognitive.learn_world_model | Online world model learning: update state transition priors from empirical execution traces. | Not declared |
| cognitive.list_experiments | Discovery: list recorded benchmark experiment IDs for cognitive.get_experiment. | Not declared |
| cognitive.matrix_algebra | Exact rational matrix & vector algebra: multiply, determinant, inverse, transpose, trace, eigenvalues, dot/cross. | Not declared |
| cognitive.monitor_reasoning | Introspective reasoning critic: inspect trace in-flight to catch cycles, invariant drift, vacuous output, and stalling. | Not declared |
| cognitive.parse_task | Convert natural-language task text into CIR and task_structure dict. Every natural-language input is normalized into CIR before reasoning. Returns both the normalized CIR and a human-readable explanation. | Not declared |
| cognitive.plan_with_counterfactuals | Synthesize the best verified plan across candidate rollouts, uncertainty tracking, and constraint pruning. | Not declared |
| cognitive.predict_world_state | Forward world model: predict future state trajectories and uncertainty bounds under actions. | Not declared |
| cognitive.project_to_manifold | Project a candidate state or plan step onto the Singular Transition Manifold M = F(S0) ∩ B(Goal). Returns the corrected state, corrective delta vector Delta S = S* - S, and boundary distance margins. | Not declared |
| cognitive.propose_strategy | Propose a candidate strategy from problem-solving experience (§24, §2). IMPORTANT: This NEVER makes the strategy TRUSTED. The strategy enters CANDIDATE state and requires objective verification. | Not declared |
| cognitive.record_experience | Record an observable event in an ongoing experience episode (§24, §7). Accepts structured actions, observations, and state changes. Never sends raw unredacted private transcripts. | Not declared |
| cognitive.refine_lattice_from_feedback | Autonomously evolve higher-order invariants, tighten bounds, and discover cliques from execution feedback. | Not declared |
| cognitive.report_transfer | Record whether a transferred strategy helped or harmed on a novel task (§24, §19). | Not declared |
| cognitive.resolve_intent | Pragmatics: resolve indirect speech acts (e.g. ability questions to directives), anaphoric pronouns, and verify presuppositions. | Not declared |
| cognitive.run_closed_loop_agent | Run the end-to-end cognitive agent closed loop (Perceive -> Model -> Decide -> Act -> Reflect -> Learn). | Not declared |
| cognitive.run_multi_agent_simulation | Simulate repeated multi-agent interaction with social dilemmas, speech acts, and reputation tracking. | Not declared |
| cognitive.safe_self_improve | Safe self-improvement: propose modifications guarded by immutable verification oracles and anchor regressions. | Not declared |
| cognitive.simulate_actions | Simulate and rank candidate actions by predicted feasibility, reward, and constraint safety. | Not declared |
| cognitive.solve_and_compare | End-to-end autonomy: identify → guide → execute → baseline → verify → verdict. Give raw task data (scheduling: workers/shifts/eligibility/capacity/ exclusivity; graph: nodes/edges; allocation: consumers/resources/...). Returns the guided solution, the unguided baseline, independent verification of both (with objective_source + independently_verified), and whether the engine improved the result. | Not declared |
| cognitive.solve_arithmetic | Evaluate or simplify mathematical expressions (PEMDAS with power, functions like sqrt, exp, log, sin, cos). | Not declared |
| cognitive.solve_equation_system | Solve linear equations (ax + b = c), quadratic equations (ax^2 + bx + c = 0), or linear systems (A x = b). | Not declared |
| cognitive.solve_word_problem | Solve math word problems (GSM8K/SVAMP/MATH) via topological constraint propagation. | Not declared |
| cognitive.start_experience | Start an experience episode (§24, §10). Does not store raw prompts or full conversations. For long-horizon work, pass parent_experience_id (+ subgoal) to chain episodes with an inherited goal stack; unknown parents are rejected, never silently adopted. | Not declared |
| cognitive.step_simulated_environment | Step an active simulated environment with an agent action. | Not declared |
| cognitive.submit_outcome | Submit the structured outcome of an experience episode (§24, §10). Triggering this may induce candidate strategies in the engine. | Not declared |
| cognitive.synthesize_program | Synthesize new algorithmic Python procedures on the fly with AST sandboxing and verification. | Not declared |
| cognitive.synthesize_singular_path | Synthesize an optimal, invariant-verified trajectory from initial state to goal through the singular bottleneck. Eliminates dead-end branching and hallucinated unfeasible solutions. | Not declared |
| cognitive.theory_of_mind | Theory of Mind: model agents' BDI mental states, test false beliefs (Sally-Anne), and infer goals via inverse planning. | Not declared |
| cognitive.tree_search | Perform Monte Carlo Tree Search (UCT) over action sequences to find optimal trajectory. | Not declared |
| cognitive.verify_arithmetic_claim | Formally verify an arithmetic equality claim, audit numerical stability, condition number, and cancellation risks. | Not declared |
| cognitive.verify_ethics_and_norms | Normative ethics & fairness: enforce deontological vetos, evaluate Rawlsian vs Utilitarian welfare, and arbitrate moral dilemmas. | Not declared |
| cognitive.verify_lattice_transition | Verify a candidate state or transition S_t -> S_{t+1} against invariant boundary manifolds. | Not declared |
| cognitive.verify_strategy | Run objective deterministic verification on a strategy (§24, §16). Clients cannot self-promote. Verification is evaluated server-side. Pass task_structure_id (from cognitive.identify_task) so constraints are independently recomputed from registered descriptors instead of trusting trace flags. Objective precedence: explicit caller value → recomputed from raw data → registered spec (labeled unknown) → nested trace claims ONLY when trust_trace_objective=true → otherwise unknown, never silent 0.0. Returns passed/score plus details.objective_source and details.independently_verified so callers know what was recomputed versus taken on trace claims. Failures are structured, never bare. | Not declared |
Change history
No changes since the first observation. The first snapshot is the baseline.
| Source | Listing | First seen | Last seen | Versions |
|---|---|---|---|---|
| Official MCP Registry | app.neotic.www/neotic | 2 Oct 2026 | 2 Oct 2026 | 1 |