15 deterministic AI agent and developer tools for code context pruning, token budgeting, hybrid search reranking, self-healing patches, AST analysis, circular dependency detection, root-cause isolation, schema compilation, math/financial solving, critical-path scheduling, A/B testing, memory diffs, API compatibility checks, boundary test generation, and Monte Carlo risk simulation.
Scored across 15 tools
Every tool has a crisply distinct resource+action, and the descriptions actively disambiguate by naming the adjacent tool to use instead (e.g. analyze_ast_symbol_graph vs audit_module_dependency_cycles, prune_context_skeleton vs plan_context_token_budget vs rerank_hybrid_rag_chunks). Even the closest pairs (evaluate_deterministic_math vs evaluate_ab_statistical_significance) are separated by explicit scope statements. An agent should almost never misselect here.
All 15 names follow the same verb_noun snake_case pattern (analyze_ast_symbol_graph, apply_fuzzy_code_patch, audit_module_dependency_cycles, ...). Verbs are chosen consistently by operation type (analyze/audit for inspection, evaluate for computation, prune/rerank/plan for context ops). No camelCase or naming-style drift anywhere.
15 tools sits at the top of the comfortable 3-15 band and each tool maps to a genuinely distinct capability, so nothing feels padded. The only mild concern is that the surface spans many loosely related domains (AST/patching, schema compilation, stats/math, scheduling, simulation, context compression), making the server broader than any single purpose.
The stated domains are covered end-to-end: analysis → patching, schema inference → breaking-change detection → test-vector generation, token planning → pruning → reranking, and deterministic math → A/B stats → Monte Carlo → CPM scheduling. Minor gaps exist (no tool to verify or re-analyze code after apply_fuzzy_code_patch, and context tools are read-only with no persistent store beyond the checkpoint diff), but agents can chain workarounds.
Static lexer and AST parser only (zero execution or evaluation): extracts imports, exports, classes, interfaces, and functions with line numbers, intra-file call edges, McCabe cyclomatic complexity, and Halstead volume across TypeScript, Python, Rust, Go, and Move. Use when mapping internal functions, call graphs, and complexity hotspots of a source file before refactoring; for analyzing cross-file import DAGs and circular dependencies, use audit_module_dependency_cycles instead. Read-only call (32 KB, 60 RPM): accepts 'source_text' (with enum defaults), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid.
Inputs: code (required), language, source_text. Returns: Deterministic response schema for analyze_ast_symbol_graph.
Applies unified diffs (@@ ... @@) or SEARCH/REPLACE blocks to source code using sliding-window token similarity to resolve drifted line numbers, align indentation, and verify bracket balance. Use when healing and applying a code edit or diff that failed exact line matching due to line-number drift or whitespace differences; for inspecting function signatures, call trees, and cyclomatic complexity without modifying code, use analyze_ast_symbol_graph instead. Read-only call (32 KB, 60 RPM): accepts 'original_code' (with enum defaults), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid.
Inputs: patch (required), original_code (required), fuzz_strategy. Returns: Deterministic response schema for apply_fuzzy_code_patch.
Runs Tarjan's Strongly Connected Components (SCC) algorithm on a module import map to detect circular dependencies, compute parallel topological build waves, and trace downstream change blast radius. Use when auditing multi-file import graphs for circular cycles or determining which downstream files must be re-tested after an edit; for extracting function-level symbols and cyclomatic complexity inside a single source file, use analyze_ast_symbol_graph instead. Read-only call (32 KB, 60 RPM): accepts 'modules_json' (with enum defaults), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid.
Inputs: modules_json (required), analysis_scope. Returns: Deterministic response schema for audit_module_dependency_cycles.
Inspects a sample JSON payload (inferring UUID, ISO-8601 datetime, email, integer vs float, and array item types) and compiles strict TypeScript interfaces, Zod schemas, Python Pydantic v2 models, and JSON Schema Draft 2020-12. Use when generating static type definitions and runtime validators in TypeScript and Python from a sample JSON response; for extracting existing function/class symbols and complexity metrics from source code, use analyze_ast_symbol_graph instead. Read-only call (32 KB, 60 RPM): accepts 'sample_json' (with enum defaults), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid.
Inputs: sample_json (required), root_name, strictness. Returns: Deterministic response schema for compile_polyglot_type_schemas.
Compares baseline and candidate OpenAPI 3.1 specs, JSON Schemas, or MCP tool manifests to detect breaking changes (removed fields, new required inputs, narrowed enums, type mutations). Use when auditing API, JSON Schema, or MCP contract revisions for backward compatibility before deployment; for compiling new TypeScript, Zod, and Pydantic schemas from a single sample JSON payload, use compile_polyglot_type_schemas instead. Read-only edge call (32 KB, 60 RPM): accepts 'baseline_schema_json' (with enum defaults), uses '?demo=true' or L402 (25 sats); HTTP 400 if invalid.
Inputs: baseline_schema_json (required), candidate_schema_json (required), contract_format. Returns: Deterministic response schema for detect_openapi_breaking_changes.
Computes structural diffs between two agent state snapshots ('added_keys', 'mutated_keys', 'removed_keys'), flags boolean belief contradictions, generates an RFC 7396 JSON Merge Patch delta, and computes a canonical checkpoint hash. Use when checkpointing agent state or transmitting minimal RFC 7396 state deltas across multi-agent handoffs; for counting BPE tokens and auditing Lost-in-the-Middle prompt attention, use plan_context_token_budget instead. Read-only call (32 KB, 60 RPM): accepts 'previous_state_json' (with enum defaults), uses '?demo=true' or L402 (10 sats); HTTP 400 if invalid.
Inputs: current_state_json (required), previous_state_json (required), conflict_strategy. Returns: Deterministic response schema for diff_agent_memory_checkpoint.
Computes Welch's two-sample t-test or two-proportion z-test, returning two-tailed p-values, Cohen's d effect size, relative lift %, and Bayesian P(Treatment > Control). Use when determining whether a prompt change, model benchmark, or A/B experiment produced a statistically significant improvement; for evaluating single algebraic formulas or NPV/IRR cashflows, use evaluate_deterministic_math instead. Read-only edge call (32 KB, 60 RPM): accepts 'control_json' ('treatment_json' defaults to 'standard'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.
Inputs: control_json (required), treatment_json (required), significance_level. Returns: Deterministic response schema for evaluate_ab_statistical_significance.
Strict Shunting-Yard AST arithmetic parser with zero eval() or dynamic code execution: evaluates algebraic formulas and computes exact financial NPV, Newton-Raphson IRR, Kelly criterion, and dataset stats. Use when computing exact arithmetic formulas, cashflow NPV/IRR, or descriptive statistics without LLM floating-point guesswork; for running two-sample A/B hypothesis tests, use evaluate_ab_statistical_significance instead. Read-only edge call (32 KB, 60 RPM): accepts 'math_formula' ('precision_digits' defaults to '2_decimals'), uses '?demo=true' or L402 (10 sats); HTTP 400 if invalid.
Inputs: expression (required), math_formula, precision_digits. Returns: Deterministic response schema for evaluate_deterministic_math.
Synthesizes deterministic unit-test vectors from a JSON Schema or function signature covering valid equivalence partitions, numeric/length boundaries, and adversarial Unicode/null inputs. Use when generating exhaustive edge-case unit test payloads and fuzz vectors for an API endpoint or function; for healing and applying unified diffs or search/replace edits to source code, use apply_fuzzy_code_patch instead. Read-only edge call (32 KB, 60 RPM): accepts 'schema_or_signature_json' (with enum defaults), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid.
Inputs: schema_or_signature_json (required), vector_suite_profile. Returns: Deterministic response schema for generate_boundary_test_vectors.
Parses noisy CI/terminal logs and multi-language stack traces (Node/TS, Python, Rust, Go), strips node_modules/stdlib frames to isolate the innermost failing user-code frame, and clusters repetitive logs into Drain templates. Use when triage-debugging test failures, crash dumps, or repetitive server error logs; for compressing general source code files or prose transcripts, use prune_context_skeleton instead. Read-only edge call (32 KB, 60 RPM): accepts 'raw_log' ('runtime_hint' defaults to 'auto_detect'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.
Inputs: raw_log (required), runtime_hint. Returns: Deterministic response schema for isolate_stacktrace_root_cause.
Counts subword BPE tokens across prompt segments, detects high-priority instructions trapped in the 35%–72% Lost-in-the-Middle attention trough, and calculates USD/satoshi costs across frontier LLMs. Use when auditing prompt token budgets, reordering prompt sections for primacy/recency attention, or comparing model API costs; for actively compressing and stripping low-salience lines from a single large file, use prune_context_skeleton instead. Read-only edge call (32 KB, 60 RPM): accepts 'segments_json' (with enum defaults), uses '?demo=true' or L402 (10 sats); HTTP 400 if invalid.
Inputs: segments_json (required), max_context_tokens, target_model_family. Returns: Deterministic response schema for plan_context_token_budget.
Compresses large source files, logs, or transcripts by 50–80% to fit an LLM context budget while preserving 100% of function/class/type signatures, imports, error frames, and query-matched lines. Use when shrinking oversized source files or logs before feeding them into an LLM prompt; for counting BPE tokens across prompt segments and calculating multi-model inference costs without altering text, use plan_context_token_budget instead. Read-only edge call (32 KB, 60 RPM): accepts 'content' (with enum defaults), uses '?demo=true' or L402 (10 sats); HTTP 400 if invalid.
Inputs: content (required), focus_query, pruning_mode, target_ratio. Returns: Deterministic response schema for prune_context_skeleton.
Reranks and deduplicates candidate RAG or retrieval passages against a search prompt using Okapi BM25 (k1=1.5, b=0.75), Reciprocal Rank Fusion (RRF), and Maximal Marginal Relevance (MMR) Jaccard diversity filtering. Use when selecting the top-K highest-signal, non-redundant passages from vector search or grep results; for compressing a single contiguous source file while keeping its original line order, use prune_context_skeleton instead. Read-only edge call (32 KB, 60 RPM): accepts 'search_prompt' ('documents_json' defaults to 'standard'), uses '?demo=true' or L402 (15 sats); HTTP 400 if invalid.
Inputs: search_prompt (required), documents_json (required), top_k, ranking_mode. Returns: Deterministic response schema for rerank_hybrid_rag_chunks.
Solves a task dependency DAG via the Critical Path Method (CPM) to compute ES/EF/LS/LF, Total Float/Slack, optimal makespan, and the Critical Path. Use when scheduling dependent engineering milestones or workflow steps to find the minimum project duration and zero-slack bottleneck path; for detecting circular code imports and file blast radius without task durations, use audit_module_dependency_cycles instead. Read-only edge call (32 KB, 60 RPM): accepts 'tasks_json' ('time_unit' defaults to 'minutes'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.
Inputs: tasks_json (required), time_unit. Returns: Deterministic response schema for schedule_critical_path_tasks.
Runs a reproducible seeded Mulberry32 Monte Carlo simulation over uncertain cost, latency, or duration variables to compute P10/P50/P90/P95 percentiles, Value-at-Risk (VaR), and CVaR. Use when modeling stochastic uncertainty, tail risk (VaR/CVaR), and probability of meeting a budget or SLA target; for evaluating deterministic single-point algebraic formulas or exact NPV/IRR cashflows, use evaluate_deterministic_math instead. Read-only edge call (32 KB, 60 RPM): accepts 'variables_json' (with enum defaults), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid.
Inputs: variables_json (required), distribution_model. Returns: Deterministic response schema for simulate_monte_carlo_risk.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Add one secure layer between your agents and this server.