Tokensave
UnclaimedThe most comprehensive code intelligence MCP server for AI coding agents. 40+ tools, 30+ languages, 9 agent integrations. Pre-indexed semantic knowledge graphs for instant code understanding — fewer tokens, fewer tool calls, 100% local.
Install
cargo install tokensave # full (50+ languages, default)Set up this server
More in AI & ML
Browse the full directoryUnclaimed listing
Is this your MCP server?
This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.
Claim this serverSecurity profile
Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works
40 of 40 tools
Documented tools (40)
From project documentation. A server handshake does not verify each tool’s description or behavior.
tokensave_affected
Find test files affected by source changes
tokensave_annotations
Attribute/annotation/decorator introspection -- histogram of all annotations or per-site listings with target filters
tokensave_ast_grep_rewrite
Structural code rewrite via the ast-grep CLI in --rewrite mode
tokensave_callees
Find what a function calls
tokensave_callers
Find what calls a function
tokensave_circular
Detect circular file dependencies
tokensave_commit_context
Semantic summary of uncommitted changes for commit message drafting
tokensave_complexity
Rank functions by cyclomatic & cognitive complexity, nesting depth, Halstead metrics, maintainability index, CRAP, and safety metrics
tokensave_context
Get relevant code context for a task -- entry points, related symbols, code snippets
tokensave_coupling
Rank files by fan-in/fan-out
tokensave_dead_code
Find unreachable symbols (no incoming edges)
tokensave_dependencies
Package-manifest introspection across 17 ecosystems -- workspace summary, per-package lookup, license surface, version drift
tokensave_dependency_depth
Longest file-level dependency chains (Lakos levelization) with full chain reconstruction after Tarjan SCC cycle-breaking
tokensave_diff_context
Semantic context for changed files -- modified symbols, dependencies, affected tests
tokensave_doc
Companion Markdown documentation for a source file -- doc content, the files it covers, and a staleness signal
tokensave_doc_coverage
Public symbols missing documentation
tokensave_dsm
Design Structure Matrix in stats, clusters, or matrix form -- reveals layering violations and hidden coupling
tokensave_files
List indexed project files (source and tracked artifacts) with filtering
tokensave_gini
Gini inequality coefficient for any metric (complexity, lines, fan-in/out, members) -- finds god files and uneven distribution
tokensave_god_class
Find classes with too many members
tokensave_health
Composite quality signal (0-10000) from acyclicity, depth, equality, redundancy, and modularity
tokensave_hotspots
Most connected symbols (highest call count)
tokensave_impact
See what's affected by changing a symbol
tokensave_imports
Module-level import dependencies, cycles, and cut simulation
tokensave_inheritance_depth
Find the deepest inheritance hierarchies
tokensave_insert_at
Insert content before or after a unique anchor string or line number
tokensave_module_api
Public API surface of a file or directory
tokensave_multi_str_replace
Apply N (old, new) replacements atomically -- all-or-nothing transaction
tokensave_node
Get details + source code for a specific symbol
tokensave_recursion
Detect recursive/mutually-recursive call cycles
tokensave_rename_preview
All references to a symbol (preview rename impact)
tokensave_search
Find symbols by name (functions, classes, types)
tokensave_session_end
Recompute and diff against the baseline -- per-dimension deltas, pass/fail, automatic cleanup
tokensave_session_start
Save current health metrics as a JSON baseline for later comparison
tokensave_similar
Find symbols with similar names
tokensave_simplify_scan
Quality analysis of changed files (duplications, dead code, complexity)
tokensave_status
Index status, statistics, tokens saved
tokensave_str_replace
Replace a unique oldstr with newstr; fails if 0 or >1 matches (protects against multi-edit bugs)
tokensave_test_risk
Risk-weighted test-gap analysis combining complexity, fan-in, coverage, and 90-day git churn into a single score
tokensave_unused_imports
Import statements never referenced
Tool change history
FAQ
Questions about Tokensave MCP Server
- How do I connect Tokensave MCP Server to Claude?
- The listing records `cargo install tokensave # full (50+ languages, default)` as its setup step. Run it, then follow the repository's instructions for the client configuration; the listing names Claude Code, Cursor, Windsurf as compatible clients.
- Is Tokensave MCP Server free?
- The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
- What can Tokensave MCP Server do?
- Tokensave MCP Server documents 40 tools to the agent, including tokensave_affected, tokensave_annotations, tokensave_ast_grep_rewrite. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.