Codecalc
未认领Universal code & logic calculator for AI models: 48 MCP tools across 31 languages. Rust-sandboxed execution with verdicts, sessions, artifacts, exact arithmetic, and verified translation/optimization. No LLM, no gateway, no telemetry: the caller is the model. Apache-2.0.
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'codecalc' -- 'uvx' 'codecalc[full]'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
40 个工具中显示 40 个
文档中列出的工具 (40)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
algebraic_equiv
Are (ab)/c and a(b/c) identical? refactor verification (with float/truncation caveat)
analyze_complexity
Static Big-O estimate from code structure, parsed with tree-sitter (every supported language). Reports analysis: tree-sitter\
bits
Programmer-mode integer facts and operations, selected by mode: analysis (was bitanalysis), op (was bitop), widths (was intwidths), repr (was baserepr) — those four former standalone tools were retired in 0.12.0 (CHANGELOG.md)
branch_reachability
python3 only. Decides, with z3, which if/elif/else arms and while/for(range, static bounds) loops in ONE function can ever be taken for ANY input — reachable/dead/unknown per branch, a witness when reachable, and boundaryinputs (min/max/equality-edge, via z3 Optimize) shaped for compareedgecases's t
calc_exact
EXACT arithmetic: 0.1+0.2 == 0.3 is True; arbitrary-precision ints, bitwise ops inline, whitelisted math funcs, pi/e/tau
calc_stats
mean, median, sample stdev, CV (CV > 0.2 = noise swamps the effect)
collision_probability
Birthday-bound hash collision: 1e5 items/32 bits ≈ 0.69, 1e6/64 ≈ 2.7e-8
compare_edge_cases
Run the same logic in N languages on edge-case inputs (empty, zero, negative, float precision) and flag behavioral divergence
compare_threshold
Exact threshold verdict with shortfall: ('1/25', '>', '0.05') → False, shortfall 1/100
convert_units
Dimensional unit conversion via sympy: length, mass, time, speed, energy, power, force, pressure, temperature (°C/°F/K), volume, area, data, frequency
data_sizes
Byte sizes both ways: KiB/MiB (binary) AND KB/MB (decimal)
epoch_time
Epoch s/ms/µs/ns → ISO 8601 UTC, implausible readings suppressed
evaluate_expression
Symbolic math: integrate(x2, x), sqrt(144) + 210
execute_code
Run code in any language → stdout/stderr/exitcode/verdict (OK/TLE/MLE/OLE/RTE)/cpums/peakmemorykb; per-call limits (maxmemorymb, maxoutputkb, maxcpu), nonet, compact. With a session and no explicit maxoutputkb, oversized output spills into the session workspace (stdoutspill/stderrspill) instead of j
execute_code_stream
Provider-selected execution using the same canonical limits as executecode, with progress + partial output when the provider supports streaming
extract_function
Pull a named function + its dependency closure (imports, referenced helpers) into a standalone program and run it (ast-exact for python3, best-effort elsewhere)
float_repr
What binary64 actually stores: exact value, raw bits, ULP, neighbours, representable-or-not
human_duration
Humanised duration + per-day/per-30d rates
install_package
Install packages (uv pip/npm/gem/go/cargo...) into a session or shared cache
list_execution_providers
Execution-provider identity, interface version, host class, and machine-readable capabilities
list_languages
31 languages with extension, compile flag, runtime availability
list_units
All 140+ unit aliases for convertunits
matrix
Structured matrix ops: det/inverse/eigenvalues/transpose/rank/trace on a rows array — never a caller string through sympify, so evaluateexpression's [/] RCE screen never applies. Each entry screened individually
percentage
Exact share and percentage of PART/TOTAL (rationals accepted)
percentiles
p50/p90/p95/p99 by nearest-rank AND interpolation; warns n<100
physical_constants
22 physical constants with values (c, h, NA, kB, G, g, me, R, ...)
radix_convert
Any base 2..36, fractions included, non-termination flagged (0.1 base 2)
run_cancel
Cancel a background run; idempotent on an already-terminal run, honest about providers that cannot cancel mid-flight
run_inspect
Poll a background run: status while running, the full executecode result shape once terminal
run_submit
Submit code for background execution; returns a runid immediately instead of holding the call open
session_artifacts
List files created by executed code (results, images, CSVs)
session_run
Multi-file programs: execute an entry file that imports other session files (helper.py, data/...) in the workspace
session_snapshot
Archive a session's workspace to a snapshot stored OUTSIDE the jailed workspace (action="save"), or restore one into a new session or, with replace=True, back into the same session (action="restore"); action="list"/"delete" manage them. Files only — never a stateful session's REPL variables. Snapsho
session_start
Persistent session; python3/node get a stateful REPL worker (variables/imports persist across calls), other languages a workspace dir
symbolic
Symbolic algebra, selected by op: solve (was solveexpression), solvelinear (was solvelinear, name unchanged), simplify (was simplifyexpression), limit (was limitexpression) — those four former standalone tools were retired in 0.12.0 (CHANGELOG.md)
trace_execution
python3 only. Runs the same sandboxed executor executecode uses, plus a per-line event trace (events: line/call/return/exception, changed locals per step) and a static branch/line-coverage report (branches, linesexecuted, linesneverexecuted) from an AST parse — answers "which lines ran, in what orde
truth_table
Boolean algebra: a and b or not c, p xor q, a implies b
verify_optimization
Prove an optimisation: you write the candidate, the executor confirms it still agrees with the original AND times both — accepted only if equivalent and measurably faster. Accepted is graded crosschecked
verify_translation
Prove a port is equivalent: you write the translation, the executor runs both versions on the same inputs and reports match / diverged / inconclusive per input. A pass is graded crosschecked (see Grade vocabulary)
z3_check
SMT-LIB2 satisfiability + model. An unsat verdict is graded solverproven; sat is graded ungraded (decided, but not proof-shaped — see Grade vocabulary)