原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

AGZ Rust Coder

作者:ugur-murat-alt版本 0.2.0i★ –i在你的电脑上运行
注册名称io.github.ugur-murat-alt/agz-rust-coder

安装

概览

作者提供的说明(英文原文)

Bounded, source-write-free Rust correctness tools grounded in Cargo and rustc output.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

  • 连接方式: 在你的电脑上运行
  • 传输方式: stdio
  • 分类: 开发者工具

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

  • 基础检查:1 项中通过 1 项
  • 在你的电脑上运行,拥有你的用户账户的权限(文件、网络、应用)。
  • 注册中心没有列出需要填写的密钥。

作者没有在注册中心列出安装信息。请查看下方作者的 README。

它能做什么

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 ugur-murat-alt 验证,该账户拥有此仓库

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

与“开发者工具”中的其他服务器比较i

  • 星标数多于此分类中其他 4912 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 4912 个服务器的 40% 更新
  • 基础检查结果等于或优于此分类中其他 4912 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

AGZ Rust Coder 安全吗?

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(0.2.0)于2个月前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Rust。

有什么可以替代它?

同一分类中有:GitHub, Desktop Commander, Cloudflare MCP

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

GitHub

作者:github

Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.

电脑或云端★ 34,245MIT4天前更新
安装

Desktop Commander

作者:wonderwhy-er

MCP server for terminal commands, file operations, and process management

在你的电脑上运行★ 10,225MIT16天前更新
安装

Cloudflare MCP

作者:cloudflare

Cloudflare MCP servers

在云端运行★ 4,446Apache-2.014个月前更新
安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

AGZ Rust MCP

English | Türkçe

An AGZ Yazılım product. agz-rust-mcp is a standalone MCP server with stdio and Streamable HTTP transports for general-purpose Rust development grounded in Cargo and rustc. Discover a project offline, collect focused source context and compiler diagnostics, select individual tests, and run binaries/examples. Exact-version dependency docs, Rust Analyzer navigation and write-free change/refactor packages support deeper work.

Everyday workflow

The same workflow works with a library, CLI, service or multi-package Cargo workspace. No framework-specific project structure or particular MCP client is required.

NeedTool call
Map packages, declared targets, features and dependencies without compilingworkspace(action="inspect")
Locate code and read bounded, numbered sourceworkspace(action="search", query="parse_record"), then workspace(action="read", path="src/lib.rs", line=1, lineCount=80)
Get fresh compiler diagnosticscheck(target="check", options={"packages":["my_crate"]})
Discover actual test namestest(action="list", packages=["my_crate"])
Run one library test by its full nametest(action="run", packages=["my_crate"], cargoTarget={"kind":"lib"}, filter="tests::parses_record", exact=true)
Compile tests without executing themtest(action="compile", packages=["my_crate"])
Execute a binary or examplerun(package="my_crate", target={"kind":"example","name":"demo"}, args=["input.json"], timeoutMs=30000)
Resolve an unfamiliar dependency APIdocs with its exact version; api for deeper resolution/probing

Pass an absolute dir for the active project when the client starts elsewhere. A function is exercised through a test or executable example. run is a typed Cargo runner; program arguments remain literal, including spaces and shell metacharacters. Tests and applications execute project code with its ordinary side effects. Empty selections return NO_TESTS, not a passing test verdict.

Use agz-rust-mcp --toolset core for a compact catalog of six everyday tools: workspace, check, test, run, docs, and crate_lookup. The default --toolset full preserves every existing tool plus the new additions. Individual --tools- false switches can disable tools further. See the full reference for limits and result states.

Install

# installer script (Linux x86_64): download install.sh and SHA256SUMS from the

latest release, verify the script, then run it

bash install.sh

crates.io (requires Rust 1.91.0 or newer)

cargo install agz-rust-mcp --locked agz-rust-mcp --version

Prebuilt .tar.gz archives with .sha256 files are available for Linux x86_64, macOS arm64, and Windows x86_64. Releases up to 0.2.0 use the legacy agz-rust-coder-* asset names; from 0.3.0 onward the names are agz-rust-mcp-*.

Step-by-step instructions, per-OS notes, checksum verification, and troubleshooting: [docs/install.md](docs/install.md) · [Türkçe](docs/install.tr.md).

MCP Client Setup

Use the installed executable with any client supporting local stdio MCP. Supply these fields in the client's own server configuration format:

{

"command": "agz-rust-mcp", "args": ["--allow-root", "/absolute/path/to/project"], "env": {"AGZ_RUST_MCP_SERVER__TOOLSET": "core"} }

For a client that uses HTTP, start the same binary as a local Streamable HTTP server and configure http://127.0.0.1:8787/mcp as its MCP URL:

agz-rust-mcp --transport http --http-bind 127.0.0.1:8787 \

--allow-root /absolute/path/to/project

The HTTP listener is loopback-only. It supports the session lifecycle used by 2025-11-25 clients and the stateless 2026-07-28 protocol. Client-side display prefixes, configuration file locations, and automatic prompt selection belong to the client; the server depends on none of them. The canonical working directory is the default authorized root; client-provided roots can only narrow configured access. See connection details.

Built-in skills

Four offline skills ship inside the executable: agz-rust-workflow, agz-rust-repair, agz-rust-refactor, and agz-rust-performance. They are available immediately through all three standard MCP interfaces:

  • Tools: workspace(action="skills") lists the catalog; workspace(action="skills", skill="agz-rust-workflow") reads a skill.
  • Prompts: prompts/list and prompts/get expose workflow, repair, refactor, and performance.
  • Resources: resources/read exposes agz-rust-mcp://skills/ .

A client that only exposes tools can use the complete skill content. Version and SHA-256 metadata identify the exact bundled instructions. No skill installation or separate MCP is required. Optional agz-rust-mcp skills export --dir creates files for clients that also support filesystem skills; existing files are never overwritten. See built-in skills.

Documentation

Read the documentation in this order:

  1. Install and client setup - every install method and client configuration.
  2. Tool and configuration reference - tools, actions, result semantics, and all configuration keys.
  3. Architecture - process model, protocol lifecycle, and authority boundaries.
  4. Validation and benchmark protocol - smokes, gates, and evidence.
  5. Security policy and Contributing.

The bilingual index with the full reading path is docs/README.md / docs/README.tr.md.

Identity

ContractValue
Crate, binary, serveragz-rust-mcp
MCP Registryio.github.agzyazilim/rust-mcp
Source version0.6.0
First release0.1.0
Release tagagz-rust-mcp-v
Rust edition / MSRV2024 / 1.91.0
Rust MCP SDKrmcp 3.8.0
Default / discovered protocol2025-11-25 / 2026-07-28

MCP package ownership marker: mcp-name: io.github.agzyazilim/rust-mcp.

Tools

These are the exact server tool names. Use the names returned by tools/list; a client may display its own namespace or prefix.

MCP toolDefaultPurpose
workspaceenabledRead built-in skills, inspect manifests/lockfiles, search source and read excerpts offline.
testenabledDiscover, compile or run selected tests with exact names, ignored-test controls and bounded execution.
runenabledRun an exact Cargo binary/example with literal arguments, a deadline and bounded output.
checkenabledRun bounded Cargo check, Clippy, tests, docs, or the full gate.
profileenabledAnalyze observed Cargo rebuild behavior and compare bounded build evidence without claiming unmeasured speedups.
auditenabledScan Rust source for bounded static findings.
crate_lookupenabledVerify a crate and optional exact version on crates.io.
docsenabledResolve exact-version docs from cache, local sources, or docs.rs.
contextenabledPrepare, expand, or delta a revision-bound semantic context capsule with per-item reasons.
apienabledResolve an API signature from bounded analyzer evidence or type-check a candidate snippet in an isolated copy of the workspace configuration.
explainenabledExplain macro expansion provenance, trait obligations, or cfg enablement.
verifyenabledPlan or run a bounded feature, target, toolchain, and stage matrix.
symbolenabledRead Rust Analyzer hover data for one symbol.
referencesenabledFind bounded references.
definitionenabledFind the selected definition.
symbolsenabledList symbols in one Rust file.
implementationsenabledFind implementations.
hierarchyenabledTrace a bounded call hierarchy.
renameenabledProduce a verified rename edit package without applying it.
refactorenabledProduce a verified refactor edit package without applying it.
changeenabledCreate, stage, migrate, and validate a revision-bound changeset in server-owned scratch without writing the workspace.
repairenabledAnalyze, try, compare, and minimize compiler-driven repair candidates for a failing change revision without writing the workspace.
workenabledDrive a typed intent through change/validate with explicit gates and budgets, returning honest gate evidence or a bounded single-use handoff.

Every tool returns deterministic structured data plus an equivalent bounded text fallback. External data stays under untrustedData. Expected domain outcomes such as compiler failure, missing crates, or unavailable docs are typed results; invalid input, authorization failure, resource exhaustion, and unavailable semantic infrastructure are protocol errors.

Configuration

Precedence is CLI, then AGZ_RUST_MCP_* environment variables, then the explicit --config TOML file, then defaults. Environment keys use __ between sections, for example AGZ_RUST_MCP_GATE__HARD_TIMEOUT_MS=600000.

KeyDefaultMeaning
server.transportstdioMCP transport: stdio or http.
server.http_bind127.0.0.1:8787Loopback address for the HTTP /mcp endpoint.
server.allow_rootscanonical CWDWorkspace read/command boundary.
server.allow_dependency_rootsemptyExplicit external path-dependency roots.
gate.hard_timeout_ms600000Cargo operation deadline.
gate.scopeshadowValidation target: workspace, shadow, or affected.
gate.cacheautoCache policy: auto, project, or isolated.
rust_analyzer.workspace_codedenyReject RA startup unless workspace code is disabled.
docs.fallbackautoDocumentation source policy.
profile.max_report_bytes4194304Bounded read/store cap for one Cargo timing artifact.
profile.max_runs4Fresh Cargo runs available to one profile call.
profile.compare_samples3Required samples per side before any speed claim.
limits.tool_output_bytes49152Maximum serialized tool result size.
change.max_bytes268435456Maximum captured candidate bytes per changeset.
repair.max_candidates4Candidates one repair action may try.
repair.max_compiles4Cargo validations one repair action may run.
repair.wall_time_ms120000Wall-clock budget for one repair action.
repair.minimize_max_candidates32Compile-evaluated reduction attempts one repair(action=minimize) may try.
repair.minimize_max_compiles16Cargo runs one repair(action=minimize) may execute, including reproduction and export verification.
work.max_candidates4Host candidate revisions one work item may stage.
work.max_compiles12Gate validations one work item may run.
work.wall_time_ms600000Wall-time budget for one work item.
telemetry.enabledtrueBounded local activity records without prompts or source.

profile evidence is bounded: the latest 64 records stay in memory, and persisted timing artifacts under the server-owned profile-evidence directory are pruned after 24 hours or beyond 64 files. The profile result reports this retention policy, so exp

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx