v0.12.0

v0.12.0: Static Analysis Engine + Auto-Fix

24 Lint Rules (was 10)

The lint command now has 24 rules that catch agent-breaking schema issues before runtime. 14 new rules added this release:

Code	What it catches
E105	Unconstrained strings flowing between tools (free text propagation)
E107	Circular dependencies in tool graph (agents loop forever)
E112	Sensitive parameters exposed (password, api_key, token)
E113	Duplicate tool names
W107	Non-deterministic output (same input, different results)
W108	Hidden side effects (name says "create" but description doesn't acknowledge)
W109	Missing examples on user-facing params (query, email, url)
W110	Schema-description drift (>50% params not mentioned in description)
W111	Description too short (<20 chars) or too long (>500 chars)
W112	Server exposes >20 tools (LLM accuracy degrades)
W114	Input schema nested >3 levels (LLMs struggle with deep nesting)
W115	Single tool consumes >1000 tokens of context
W116	Description doesn't mention what tool returns
(overloaded)	>3 action verbs in description (tool does too many things)

Auto-Fix (--fix)

Generate schema improvement suggestions automatically:

mcp-assert lint --server "npx my-server" --fix

memory-server: 9 tools, 25 findings, 23 auto-fixable

  E103   create_entities   Add description: "The entities value (array)"
  W109   search_nodes      Add examples to "query": [search term]
  W116   read_graph        Append: "Returns the graph data as JSON."

23 fixes generated.

Infers descriptions from tool names, formats from param patterns (email, uuid, date-time), examples from common names, and return clauses from verbs. JSON output with --fix --json.

--strict Mode

Promote all warnings to errors for CI gates:

mcp-assert lint --server "..." --strict
# 16 error(s), 0 warning(s)

--detect-nondeterminism

Calls each tool 3x with identical inputs, compares output hashes. Flags tools that produce different results across runs.

Tool Dependency Graph

Infers data-flow dependencies between tools by matching parameter names, types, and description tokens. Powers E105 (free text propagation) and E107 (circular dependency). Generic parameters excluded to prevent false positives.

Unified Error Taxonomy

All commands now share a single error code registry. Audit output shows structured codes:

✓ read_query      1ms  [E000] responds, returns content
✗ create_table    0ms  [E201] internal error: panic: nil pointer...

Scorecard Validation

Tested on 6 servers: memory (92% fix rate), filesystem (72%), sqlite (94%), time (60%), antvis-chart, fetch (75%).

Full Changelog: v0.11.0...v0.12.0