Neotic MCP server

• cognitive.allocate_computeFree

  Adaptive compute budgeting: select compute tier (Fast Path to Deep Deliberation) and timeout based on EVC.

• cognitive.analogical_transferwrite actionFree

  Transfer structural strategies across disparate domains via Structure-Mapping Engine (SME).

• cognitive.analyze_communicationFree

  Pragmatic communication: audit speech acts against Gricean maxims (Quality, Quantity, Relation, Manner) and detect deception.

• cognitive.arbitrate_temporal_objectivesFree

  Arbitrate short vs long term payoffs using hyperbolic vs exponential discounting and Ulysses pre-commitment contracts.

• cognitive.assess_competenceFree

  Epistemic boundary awareness: classify task into KNOWN, KNOWN_UNKNOWN, or UNKNOWN_UNKNOWN (OOD) and track calibration.

• cognitive.audit_evidence_graphFree

  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.

• cognitive.build_evidence_graphFree

  Build or update an Evidence-Carrying Cognitive Graph for a task structure and solution trace.

• cognitive.causal_analysisFree

  Distinguish causal effects (do-calculus) from spurious correlation via backdoor adjustment.

• cognitive.compile_invariant_latticeFree

  Compile a Dynamic Constraint Lattice (DCL) into algebraic boundaries, conservation laws, and reachability cones.

• cognitive.compose_strategiesFree

  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.

• cognitive.compute_intrinsic_rewardsFree

  Compute intrinsic drives: novelty & prediction surprise curiosity, empowerment (channel capacity), and learning progress.

• cognitive.compute_lattice_signatureFree

  Compute coordinate-free topological invariant signature of a lattice or task.

• cognitive.compute_number_theoryFree

  Number theory: primality, factoring, extended GCD, Diophantine, modular inverse, CRT, combinatorics, Fibonacci.

• cognitive.counterfactual_what_ifFree

  Counterfactual engine: evaluate 'What if I had done X instead of Y at step t?' using Pearl's abduction-intervention-prediction.

• cognitive.create_simulated_environmentwrite actionFree

  Instantiate and initialize a simulated cognitive environment (spatial_commons, multi_agent_arena, sequential_puzzle).

• cognitive.crucible_stress_testFree

  Subject candidate trajectories to adversarial algebraic perturbations to calculate Robustness Index (R) and project hardened paths.

• cognitive.evaluate_claim_evidenceFree

  Evaluate support status and confidence for an individual claim with evidence.

• cognitive.evaluate_cooperationFree

  Multi-agent cooperation: analyze game payoff matrices, compute Nash/Pareto equilibria, and execute reciprocity policies.

• cognitive.evaluate_counterfactual_queryFree

  Evaluate a counterfactual query on a plan ('What if capacity drops?', 'What if a route fails?', etc.).

• cognitive.evaluate_generalization_benchmarksFree

  Evaluate broad generalization across spatial commons, multi-agent arenas, and sequential causal puzzles.

• cognitive.execute_taskwrite actionFree

  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.

• cognitive.few_shot_induceFree

  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.

• cognitive.generate_and_prioritize_goalsFree

  Autonomous goal synthesis from world deficits, depleted reserves, and exploration frontiers with multi-criteria prioritization.

• cognitive.get_experimentFree

  Retrieve details and benchmark results of an experiment (§24, §69).

• cognitive.get_final_evidence_resultFree

  Compile a final evidence result listing supporting evidence, assumptions, missing evidence, contradictions, unchecked dependencies, confidence, and invalidation conditions.

• cognitive.get_guidanceFree

  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.

• cognitive.get_strategyFree

  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).

• cognitive.get_strategy_reportFree

  Evidence dossier: baseline vs assisted, distribution, CI, failures, last eval.

• cognitive.ground_languageFree

  Non-LLM compositional semantics: parse utterance into semantic predicates and evaluate directly against WorldState.

• cognitive.hierarchical_planFree

  Decompose high-level goals into milestone subgoals using Hierarchical Task Network (HTN) planning.

• cognitive.identify_taskwrite actionFree

  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.

• cognitive.induce_morphic_transferwrite actionFree

  Discover topological homomorphism between source experience and target problem, transducing solution paths.

• cognitive.inferFree

  Perform logical deduction (Horn clauses) or exact probabilistic Bayesian network inference.

• cognitive.infer_human_valuesFree

  Infer human values via Bradley-Terry IRL, detect Goodhart's law / specification gaming, and assess CIRL deference.

• cognitive.inspect_lexiconFree

  Inspect grounded lexicon acquired via situated interaction (learned vocabulary, concept bindings, confidence).

• cognitive.inspect_self_modelFree

  Engine self-model introspection: inspect capabilities, domain competence, active subsystems, and safety status.

• cognitive.learn_from_mistakeFree

  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.

• cognitive.learn_language_interactionFree

  Interactive language acquisition: learn word-concept bindings through cross-situational observation, games, and feedback.

• cognitive.learn_world_modelFree

  Online world model learning: update state transition priors from empirical execution traces.

• cognitive.list_experimentsFree

  Discovery: list recorded benchmark experiment IDs for cognitive.get_experiment.

• cognitive.matrix_algebraFree

  Exact rational matrix & vector algebra: multiply, determinant, inverse, transpose, trace, eigenvalues, dot/cross.

• cognitive.monitor_reasoningFree

  Introspective reasoning critic: inspect trace in-flight to catch cycles, invariant drift, vacuous output, and stalling.

• cognitive.parse_taskFree

  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.

• cognitive.plan_with_counterfactualsFree

  Synthesize the best verified plan across candidate rollouts, uncertainty tracking, and constraint pruning.

• cognitive.predict_world_stateFree

  Forward world model: predict future state trajectories and uncertainty bounds under actions.

• cognitive.project_to_manifoldFree

  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.

• cognitive.propose_strategyFree

  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.

• cognitive.record_experienceFree

  Record an observable event in an ongoing experience episode (§24, §7). Accepts structured actions, observations, and state changes. Never sends raw unredacted private transcripts.

• cognitive.refine_lattice_from_feedbackFree

  Autonomously evolve higher-order invariants, tighten bounds, and discover cliques from execution feedback.

• cognitive.report_transferwrite actionFree

  Record whether a transferred strategy helped or harmed on a novel task (§24, §19).

• cognitive.resolve_intentFree

  Pragmatics: resolve indirect speech acts (e.g. ability questions to directives), anaphoric pronouns, and verify presuppositions.

• cognitive.run_closed_loop_agentwrite actionFree

  Run the end-to-end cognitive agent closed loop (Perceive -> Model -> Decide -> Act -> Reflect -> Learn).

• cognitive.run_multi_agent_simulationwrite actionFree

  Simulate repeated multi-agent interaction with social dilemmas, speech acts, and reputation tracking.

• cognitive.safe_self_improveFree

  Safe self-improvement: propose modifications guarded by immutable verification oracles and anchor regressions.

• cognitive.simulate_actionsFree

  Simulate and rank candidate actions by predicted feasibility, reward, and constraint safety.

• cognitive.solve_and_compareFree

  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.

• cognitive.solve_arithmeticFree

  Evaluate or simplify mathematical expressions (PEMDAS with power, functions like sqrt, exp, log, sin, cos).

• cognitive.solve_equation_systemFree

  Solve linear equations (ax + b = c), quadratic equations (ax^2 + bx + c = 0), or linear systems (A x = b).

• cognitive.solve_word_problemFree

  Solve math word problems (GSM8K/SVAMP/MATH) via topological constraint propagation.

• cognitive.start_experienceFree

  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.

• cognitive.step_simulated_environmentFree

  Step an active simulated environment with an agent action.

• cognitive.submit_outcomewrite actionFree

  Submit the structured outcome of an experience episode (§24, §10). Triggering this may induce candidate strategies in the engine.

• cognitive.synthesize_programFree

  Synthesize new algorithmic Python procedures on the fly with AST sandboxing and verification.

• cognitive.synthesize_singular_pathFree

  Synthesize an optimal, invariant-verified trajectory from initial state to goal through the singular bottleneck. Eliminates dead-end branching and hallucinated unfeasible solutions.

• cognitive.theory_of_mindFree

  Theory of Mind: model agents' BDI mental states, test false beliefs (Sally-Anne), and infer goals via inverse planning.

• cognitive.tree_searchFree

  Perform Monte Carlo Tree Search (UCT) over action sequences to find optimal trajectory.

• cognitive.verify_arithmetic_claimFree

  Formally verify an arithmetic equality claim, audit numerical stability, condition number, and cancellation risks.

• cognitive.verify_ethics_and_normsFree

  Normative ethics & fairness: enforce deontological vetos, evaluate Rawlsian vs Utilitarian welfare, and arbitrate moral dilemmas.

• cognitive.verify_lattice_transitionFree

  Verify a candidate state or transition S_t -> S_{t+1} against invariant boundary manifolds.

• cognitive.verify_strategywrite actionFree

  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.

• cognitive_allocate_computeFree

  Adaptive compute budgeting: select compute tier (Fast Path to Deep Deliberation) and timeout based on EVC.

• cognitive_analogical_transferwrite actionFree

  Transfer structural strategies across disparate domains via Structure-Mapping Engine (SME).

• cognitive_analyze_communicationFree

  Pragmatic communication: audit speech acts against Gricean maxims (Quality, Quantity, Relation, Manner) and detect deception.

• cognitive_arbitrate_temporal_objectivesFree

  Arbitrate short vs long term payoffs using hyperbolic vs exponential discounting and Ulysses pre-commitment contracts.

• cognitive_assess_competenceFree

  Epistemic boundary awareness: classify task into KNOWN, KNOWN_UNKNOWN, or UNKNOWN_UNKNOWN (OOD) and track calibration.

• cognitive_audit_evidence_graphFree

  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.

• cognitive_build_evidence_graphFree

  Build or update an Evidence-Carrying Cognitive Graph for a task structure and solution trace.

• cognitive_causal_analysisFree

  Distinguish causal effects (do-calculus) from spurious correlation via backdoor adjustment.

• cognitive_compile_invariant_latticeFree

  Compile a Dynamic Constraint Lattice (DCL) into algebraic boundaries, conservation laws, and reachability cones.

• cognitive_compose_strategiesFree

  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.

• cognitive_compute_intrinsic_rewardsFree

  Compute intrinsic drives: novelty & prediction surprise curiosity, empowerment (channel capacity), and learning progress.

• cognitive_compute_lattice_signatureFree

  Compute coordinate-free topological invariant signature of a lattice or task.

• cognitive_compute_number_theoryFree

  Number theory: primality, factoring, extended GCD, Diophantine, modular inverse, CRT, combinatorics, Fibonacci.

• cognitive_counterfactual_what_ifFree

  Counterfactual engine: evaluate 'What if I had done X instead of Y at step t?' using Pearl's abduction-intervention-prediction.

• cognitive_create_simulated_environmentwrite actionFree

  Instantiate and initialize a simulated cognitive environment (spatial_commons, multi_agent_arena, sequential_puzzle).

• cognitive_crucible_stress_testFree

  Subject candidate trajectories to adversarial algebraic perturbations to calculate Robustness Index (R) and project hardened paths.

• cognitive_evaluate_claim_evidenceFree

  Evaluate support status and confidence for an individual claim with evidence.

• cognitive_evaluate_cooperationFree

  Multi-agent cooperation: analyze game payoff matrices, compute Nash/Pareto equilibria, and execute reciprocity policies.

• cognitive_evaluate_counterfactual_queryFree

  Evaluate a counterfactual query on a plan ('What if capacity drops?', 'What if a route fails?', etc.).

• cognitive_evaluate_generalization_benchmarksFree

  Evaluate broad generalization across spatial commons, multi-agent arenas, and sequential causal puzzles.

• cognitive_execute_taskwrite actionFree

  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.

• cognitive_few_shot_induceFree

  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.

• cognitive_generate_and_prioritize_goalsFree

  Autonomous goal synthesis from world deficits, depleted reserves, and exploration frontiers with multi-criteria prioritization.

• cognitive_get_experimentFree

  Retrieve details and benchmark results of an experiment (§24, §69).

• cognitive_get_final_evidence_resultFree

  Compile a final evidence result listing supporting evidence, assumptions, missing evidence, contradictions, unchecked dependencies, confidence, and invalidation conditions.

• cognitive_get_guidanceFree

  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.

• cognitive_get_strategyFree

  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).

• cognitive_get_strategy_reportFree

  Evidence dossier: baseline vs assisted, distribution, CI, failures, last eval.

• cognitive_ground_languageFree

  Non-LLM compositional semantics: parse utterance into semantic predicates and evaluate directly against WorldState.

• cognitive_hierarchical_planFree

  Decompose high-level goals into milestone subgoals using Hierarchical Task Network (HTN) planning.

• cognitive_identify_taskwrite actionFree

  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.

• cognitive_induce_morphic_transferwrite actionFree

  Discover topological homomorphism between source experience and target problem, transducing solution paths.

• cognitive_inferFree

  Perform logical deduction (Horn clauses) or exact probabilistic Bayesian network inference.

• cognitive_infer_human_valuesFree

  Infer human values via Bradley-Terry IRL, detect Goodhart's law / specification gaming, and assess CIRL deference.

• cognitive_inspect_lexiconFree

  Inspect grounded lexicon acquired via situated interaction (learned vocabulary, concept bindings, confidence).

• cognitive_inspect_self_modelFree

  Engine self-model introspection: inspect capabilities, domain competence, active subsystems, and safety status.

• cognitive_learn_from_mistakeFree

  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.

• cognitive_learn_language_interactionFree

  Interactive language acquisition: learn word-concept bindings through cross-situational observation, games, and feedback.

• cognitive_learn_world_modelFree

  Online world model learning: update state transition priors from empirical execution traces.

• cognitive_list_experimentsFree

  Discovery: list recorded benchmark experiment IDs for cognitive.get_experiment.

• cognitive_matrix_algebraFree

  Exact rational matrix & vector algebra: multiply, determinant, inverse, transpose, trace, eigenvalues, dot/cross.

• cognitive_monitor_reasoningFree

  Introspective reasoning critic: inspect trace in-flight to catch cycles, invariant drift, vacuous output, and stalling.

• cognitive_parse_taskFree

  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.

• cognitive_plan_with_counterfactualsFree

  Synthesize the best verified plan across candidate rollouts, uncertainty tracking, and constraint pruning.

• cognitive_predict_world_stateFree

  Forward world model: predict future state trajectories and uncertainty bounds under actions.

• cognitive_project_to_manifoldFree

  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.

• cognitive_propose_strategyFree

  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.

• cognitive_record_experienceFree

  Record an observable event in an ongoing experience episode (§24, §7). Accepts structured actions, observations, and state changes. Never sends raw unredacted private transcripts.

• cognitive_refine_lattice_from_feedbackFree

  Autonomously evolve higher-order invariants, tighten bounds, and discover cliques from execution feedback.

• cognitive_report_transferwrite actionFree

  Record whether a transferred strategy helped or harmed on a novel task (§24, §19).

• cognitive_resolve_intentFree

  Pragmatics: resolve indirect speech acts (e.g. ability questions to directives), anaphoric pronouns, and verify presuppositions.

• cognitive_run_closed_loop_agentwrite actionFree

  Run the end-to-end cognitive agent closed loop (Perceive -> Model -> Decide -> Act -> Reflect -> Learn).

• cognitive_run_multi_agent_simulationwrite actionFree

  Simulate repeated multi-agent interaction with social dilemmas, speech acts, and reputation tracking.

• cognitive_safe_self_improveFree

  Safe self-improvement: propose modifications guarded by immutable verification oracles and anchor regressions.

• cognitive_simulate_actionsFree

  Simulate and rank candidate actions by predicted feasibility, reward, and constraint safety.

• cognitive_solve_and_compareFree

  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.

• cognitive_solve_arithmeticFree

  Evaluate or simplify mathematical expressions (PEMDAS with power, functions like sqrt, exp, log, sin, cos).

• cognitive_solve_equation_systemFree

  Solve linear equations (ax + b = c), quadratic equations (ax^2 + bx + c = 0), or linear systems (A x = b).

• cognitive_solve_word_problemFree

  Solve math word problems (GSM8K/SVAMP/MATH) via topological constraint propagation.

• cognitive_start_experienceFree

  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.

• cognitive_step_simulated_environmentFree

  Step an active simulated environment with an agent action.

• cognitive_submit_outcomewrite actionFree

  Submit the structured outcome of an experience episode (§24, §10). Triggering this may induce candidate strategies in the engine.

• cognitive_synthesize_programFree

  Synthesize new algorithmic Python procedures on the fly with AST sandboxing and verification.

• cognitive_synthesize_singular_pathFree

  Synthesize an optimal, invariant-verified trajectory from initial state to goal through the singular bottleneck. Eliminates dead-end branching and hallucinated unfeasible solutions.

• cognitive_theory_of_mindFree

  Theory of Mind: model agents' BDI mental states, test false beliefs (Sally-Anne), and infer goals via inverse planning.

• cognitive_tree_searchFree

  Perform Monte Carlo Tree Search (UCT) over action sequences to find optimal trajectory.

• cognitive_verify_arithmetic_claimFree

  Formally verify an arithmetic equality claim, audit numerical stability, condition number, and cancellation risks.

• cognitive_verify_ethics_and_normsFree

  Normative ethics & fairness: enforce deontological vetos, evaluate Rawlsian vs Utilitarian welfare, and arbitrate moral dilemmas.

• cognitive_verify_lattice_transitionFree

  Verify a candidate state or transition S_t -> S_{t+1} against invariant boundary manifolds.

• cognitive_verify_strategywrite actionFree

  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.

• –Code scanremote-only server, no package to scann/a
• Live reliabilityremote reachable in 1664ms20/20
• Tool poisoning140 tool descriptions checked15/15
• Auth qualityopen endpoint exposes 20 write-action tools with no auth3/15
• Maintenanceno repository listed3/15
• Maintainer identityverified namespace with website, no repo4/10

Neotic: common questions

Is Neotic MCP server safe?

With care: it is graded C, so read the findings first (60/100). Read the Neotic safety report

How do I install Neotic?

It runs remotely at www.neotic.app. Add it to Claude Code, Claude Desktop or Cursor with the snippets above, or call it through the mcp.market gateway without installing anything.

Does Neotic need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Neotic maintained?

The latest release is v1.0.0.

Is Neotic up?

100% of our last 20 checks got an answer. We check remote servers about four times a day.