公共托管服务器： https://toolkit.caseyjhand.com/mcp
七个工具。其中五个始终可用，无需任何配置——纯计算工具加上一个无 SSRF 风险的 IP 查询工具。另外两个会探测服务器主机，在 tools/list 中默认不出现，除非你主动启用，且默认关闭（fail-closed）。
工具 | 描述 |
| 生成加密摘要（sha256/sha512/sha1/md5），或对值进行常量时间比较，与预期摘要进行比对。 |
| 生成加密随机标识符——UUIDv4、UUIDv7 或 ULID——可单个生成，也可批量生成最多 1000 个。 |
| 将文本或 URL 编码为 QR 码，输出格式为 SVG 标记、base64 PNG 或终端可渲染字符串。 |
| 对值进行编码或解码，支持 base64、base64url、hex 或 URL 百分比编码，可双向操作。 |
| 将公共 IP 或主机名解析为地理和网络元数据——国家、城市、坐标、ASN、时区。 |
| 受限，默认关闭。 只读网络诊断，从服务器主机执行——ping、traceroute、TCP 连接性或出口 IP 检测。 |
| 受限，默认关闭。 报告服务器主机系统状态的某个方面——操作系统、CPU、内存、平均负载或网络接口。 |
toolkit_hash_value生成摘要，或对值进行常量时间验证，与预期值比对。
operation：generate（小写十六进制摘要）或 compare（通过 timingSafeEqual 进行时序安全检查）
算法：sha256（默认）和 sha512 用于安全场景；sha1 和 md5 仅用于校验和和文件完整性兼容——绝不可用于密码或签名
inputEncoding 将 value 视为 utf8（默认）、hex 或 base64，因此二进制数据可跳过一轮解码往返
典型用法：将下载文件与供应商发布的校验和进行匹配
toolkit_generate_id从平台 CSPRNG 生成加密随机标识符——这是生成不可预测 ID 的正确来源，不同于模型自行构造的值。
type：uuid_v4（随机，默认）、uuid_v7（按创建时间排序，可排序）或 ulid（26 个字符的 Crockford base32，按字典序可排序）
count 可在一次调用中批量生成最多 1000 个；返回的 ids 数组始终恰好包含 count 个值
uuid_v7 和 ulid 批次是单调递增的——即使在同一毫秒内也严格递增——因此 ids 保持按创建顺序排序
只读——生成操作不改变任何状态——但绝不幂等，因此客户端不会缓存或去重一个批次
toolkit_generate_qr将文本或 URL 编码为 QR 码。
format：svg（内联标记）、png_base64（带有 mimeType 和 byteLength 的栅格字节）或 terminal（Unicode 块字符字符串）
errorCorrection（L/M/Q/H）在数据容量与容错能力之间权衡；margin 设置静区宽度；scale 设置栅格输出的每模块像素数
返回的 version（1–40）反映编码数据的密度
png_base64 还会作为 MCP 图像内容块提供，因此读取 content[] 的客户端无需解码 structuredContent 即可渲染二维码
渲染的 PNG 每边限制在 2048 像素以内——(modules + 2 × margin) × scale——因此高密度符号在较大 scale 下会被拒绝，并返回带有 raster_too_large 类型的错误，提示一个合适的 scale 值；svg 和 terminal 无此限制
data 最大为 2953 字节——绝对上限（版本 40，L 级，字节模式）；在更高的 errorCorrection 级别下可用容量更低，因此超出容量的输入会被拒绝，并返回带有 data_too_large 类型的错误，而非通用失败
toolkit_encode_value对值进行编码或解码，支持双向操作。
encoding：base64、base64url（URL 安全字母表）、hex 或 url（百分比编码）
operation：encode（原始 UTF-8 → 编码）或 decode（编码值 → 文本）
格式错误的解码输入返回带有 decode_failed 类型的错误及恢复提示，而非静默尽力解码
toolkit_geolocate_ip将公共 IP 或主机名解析为地理和网络元数据。
返回国家、地区、城市、纬度/经度、ASN、所属组织及时区
proxy、hosting 和 mobile 标志用于指示地址是否为代理/VPN/Tor 出口、数据中心网络或移动运营商——其中任何一个为 true 表示坐标描述的是基础设施，而非个人。当提供商未报告时，这些字段不存在
主机名首先通过 DNS 解析；resolvedIp 回显实际定位的 IP，source 指明提供方名称
无 SSRF——服务器调用的是提供方，永远不会调用目标地址；解析后的 IP 会再次检查是否为私有地址，私有/保留地址会被拒绝（它们没有公共地理定位信息）
尽力而为且受限于提供方：VPN、代理、移动 NAT 和任播都会影响 IP 定位，精度最多到城市级别，缺失字段报告为未知而非编造
提供方提供的字符串会被截断并去除控制字符后才进入响应，因此注册中心控制的文本（org、isp、as）不会淹没或影响模型上下文格式
默认无需密钥（ip-api 免费版，使用明文 HTTP——参见 TOOLKIT_GEO_BASE_URL）；结果按解析后的 IP 缓存于内存中，并有固定条目上限
toolkit_check_network受限——仅在 TOOLKIT_ENABLE_NET_DIAGNOSTICS=true 时注册。只读网络诊断，从服务器主机执行。
mode：ping（ICMP 往返）、traceroute（到目标的跃点路径）、connectivity（向 target 的 port 进行原始 TCP 连接）或 public_ip（主机自身的出口 IP）
无响应的主机报告为 reachable: false——这是一个有效结果，而非错误
诊断的是服务器自身的网络，因此在本地或自托管部署中很有用；要访问私有/保留/内部目标，还需 TOOLKIT_ALLOW_PRIVATE_NETWORK=true，这默认会阻止云元数据端点
toolkit_check_system受限——仅在 TOOLKIT_ENABLE_SYSTEM_INFO=true 时注册。报告服务器主机系统状态的某个方面，只读。
what：os、cpu、memory、load 或 interfaces
每次调用只填充一个方面对象，与 what 匹配
描述的是运行此服务器的主机，而非调用客户端——在本地或自托管部署中有意义；默认关闭，因为 os 和 interfaces 会暴露主机拓扑和版本细节
Related MCP server: IT Tools MCP Server
基于 @cyanheads/mcp-ts-core 构建：
声明式工具定义——每个工具一个文件，框架负责注册和验证
统一错误处理——处理函数抛出错误，框架捕获、分类并格式化
类型化错误契约——每个可能失败的工具都会声明其失败原因，并附带代理可操作的恢复提示
可插拔认证：none、jwt、oauth
结构化日志，可选 OpenTelemetry 追踪
STDIO 和 Streamable HTTP 传输
工具包特有：
默认关闭的防护机制——两个探测主机的工具在 tools/list 中不出现，除非显式启用，因此托管实例不会暴露 SSRF 或信息泄露面
双层网络防护——即使启用了诊断，私有/保留/回环/链路本地目标（包括云元数据端点）也保持阻断，直到第二个标志允许它们
CSPRNG 支持的原语——标识符和摘要来自平台加密源，哈希比较通过 timingSafeEqual 实现常量时间比较
无 SSRF 的地理定位——服务器调用提供方，然后在查询前再次检查 DNS 解析后的 IP 是否在私有范围，因此主机名无法将请求走私到内部地址
对代理友好的输出：
来源追溯——地理定位回显解析后的 IP 并指明提供方名称；上游缺失字段报告为未知，绝不编造
故障但有效的结果——不可达主机返回 reachable: false 而非错误，因此调用者基于数据进行分支判断，而非异常文本
类型化失败原因——解码失败、缺失摘要和被阻止的私有目标各自携带结构化的原因及下一步恢复提示
公共实例地址为 https://toolkit.caseyjhand.com/mcp——无需安装。通过 Streamable HTTP 将任何 MCP 客户端指向该地址：
{
"mcpServers": {
"toolkit-mcp-server": {
"type": "streamable-http",
"url": "https://toolkit.caseyjhand.com/mcp"
}
}
}将以下内容添加到您的 MCP 客户端配置文件中。无需 API 密钥——五个始终可用的工具和默认的无密钥地理定位层开箱即用。
{
"mcpServers": {
"toolkit-mcp-server": {
"type": "stdio",
"command": "bunx",
"args": ["@cyanheads/toolkit-mcp-server@latest"],
"env": {
"MCP_TRANSPORT_TYPE": "stdio",
"MCP_LOG_LEVEL": "info"
}
}
}
}或者使用 npx（无需 Bun）：
{
"mcpServers": {
"toolkit-mcp-server": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@cyanheads/toolkit-mcp-server@latest"],
"env": {
"MCP_TRANSPORT_TYPE": "stdio",
"MCP_LOG_LEVEL": "info"
}
}
}
}或者使用 Docker：
{
"mcpServers": {
"toolkit-mcp-server": {
"type": "stdio",
"command": "docker",
"args": ["run", "-i", "--rm", "-e", "MCP_TRANSPORT_TYPE=stdio", "ghcr.io/cyanheads/toolkit-mcp-server:latest"]
}
}
}要启用受限制的主机探测工具，请将相应的标志添加到 env（或 Docker 的 -e）：
"env": {
"MCP_TRANSPORT_TYPE": "stdio",
"TOOLKIT_ENABLE_NET_DIAGNOSTICS": "true",
"TOOLKIT_ENABLE_SYSTEM_INFO": "true"
}对于 Streamable HTTP，设置传输方式并启动服务器：
MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcpBun v1.3.2 或更高版本（或 Node.js v24+）。
无需 API 密钥——地理定位默认使用无密钥的 ip-api 免费版。
克隆仓库：
git clone https://github.com/cyanheads/toolkit-mcp-server.git进入目录：
cd toolkit-mcp-server安装依赖：
bun install每个变量都是可选的。服务器特定的选项在启动时通过 src/config/server-config.ts 中的 Zod 模式进行验证。
变量 | 描述 | 默认值 |
| 注册受门控的 |
|
| 注册受门控的 |
|
| 启用网络诊断时，允许私有/保留/回环目标。这是第二道显式门控。 |
|
| 地理定位端点的 API 密钥（如果需要）。 | 无 |
| 兼容 ip-api 的地理定位端点的基础 URL。默认是明文 HTTP——ip-api 的 HTTPS 端点不属于无密钥免费套餐，如果没有付费密钥，会返回 |
|
| 内存中地理定位缓存的 TTL（秒）。 |
|
| 每分钟最大地理定位请求数。 |
|
| 传输方式： |
|
| HTTP 服务器的端口。 |
|
| 认证模式： |
|
| 日志级别（RFC 5424）。 |
|
| 启用 OpenTelemetry 检测（跨度、指标、完成日志）。 |
|
请参阅 .env.example 获取完整的可选覆盖列表。
构建并运行：
# One-time build
bun run rebuild
# Run the built server
bun run start:stdio
# or
bun run start:http运行检查和测试：
bun run devcheck # Lint, format, typecheck, security, changelog sync
bun run test # Vitest test suite
bun run lint:mcp # Validate MCP definitions against specdocker build -t toolkit-mcp-server .
docker run --rm -e MCP_TRANSPORT_TYPE=http -p 3010:3010 toolkit-mcp-serverDockerfile 默认使用 HTTP 传输、无状态会话模式，并将日志记录到 /var/log/toolkit-mcp-server。OpenTelemetry 对等依赖项默认安装——使用 --build-arg OTEL_ENABLED=false 构建以省略它们。
目录 | 用途 |
|
|
| 使用 Zod 进行服务器特定的环境变量解析和验证。 |
| 工具定义（ |
| 地理定位服务——DNS 解析、带重试/退避的提供商调用、标准化、内存缓存。 |
| 网络诊断服务，以及共享的目标验证器和私有范围分类器。 |
| 单元测试和集成测试，镜像 |
请参阅 CLAUDE.md / AGENTS.md 获取开发指南和架构规则。简要说明：
处理程序抛出异常，框架捕获——工具逻辑中不使用 try/catch
使用 ctx.log 进行请求范围的日志记录，使用 ctx.state 进行租户范围的存储
在 src/index.ts 的 createApp() 数组中注册新工具
两个主机探测工具在其启用标志后注册；网络目标门控在 DNS 解析后验证——切勿为无法定位或无法访问的目标伪造结果
欢迎提交 Issue 和 Pull Request。提交前请运行检查和测试：
bun run devcheck
bun run testApache-2.0——详情请参阅 LICENSE。
Encode or decode a value across base64, base64url, hex, or URL (percent) encoding, in either direction. Set operation to "encode" to transform raw UTF-8 text into the chosen encoding, or "decode" to recover the original bytes from an encoded value. Decoded bytes come back as UTF-8 text by default; set outputEncoding to "hex" or "base64" to receive them re-encoded instead, which is lossless for binary data and transcodes between encodings (a base64 digest to hex, for example). Decoding never substitutes replacement characters: bytes that are not valid UTF-8 text are reported as a recoverable error that points at outputEncoding. Whitespace in hex, base64, and base64url values is ignored, so line-wrapped MIME bodies and PEM bodies decode as-is (drop PEM's -----BEGIN/END----- lines, which are not base64). base64url uses the URL-safe alphabet (- and _ instead of + and /); url applies encodeURIComponent and percent-decoding. A value that is malformed for the chosen encoding is reported as a recoverable error, not a silent best-effort.
| Name | Required | Description | Default |
|---|---|---|---|
| value | Yes | The value to transform — raw text for encode, an encoded string for decode. Whitespace is ignored when decoding hex, base64, or base64url; a url value is taken literally. | |
| encoding | Yes | The encoding to apply: base64, URL-safe base64url, hex, or URL percent-encoding. | |
| operation | Yes | "encode" transforms text into the encoding; "decode" recovers the bytes from an encoded value. | |
| outputEncoding | No | Decode only: how the recovered bytes are returned. utf8 (used when omitted) returns text and fails when the bytes are not valid UTF-8; hex and base64 return the raw bytes re-encoded, losslessly. Rejected when operation is "encode". |
| Name | Required | Description |
|---|---|---|
| error | No | Present when the call failed. Absent on success. |
| result | No | The transformed value: encoded text for encode; for decode, the recovered bytes as UTF-8 text, hex, or base64 per outputEncoding. |
| encoding | No | The encoding that was applied. |
| operation | No | The operation that was performed. |
| outputEncoding | No | How result renders the decoded bytes: utf8 text, hex, or base64. Present for operation "decode". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description goes far beyond the readOnlyHint/idempotentHint annotations by disclosing key behavior: decoding never substitutes replacement characters, malformed values produce recoverable errors, whitespace is ignored in certain encodings, base64url uses the URL-safe alphabet, and url uses encodeURIComponent. This is exactly the kind of behavioral context an agent needs beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is longer than average but every sentence carries useful information, including edge cases, error behavior, and encoding-specific details. The first sentence front-loads the core purpose. It is dense rather than redundant, though it could be tightened slightly without losing value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity — four parameters, three enums, two operations, and multiple encoding formats — the description is remarkably complete. It covers error handling, whitespace tolerance, PEM/MIME scenarios, binary data handling, and output format options. With an output schema also present, nothing an agent needs to call and understand this tool is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Even though schema coverage is 100%, the description adds substantial meaning to the parameters: it explains what "decode" returns by default, how outputEncoding enables lossless transcoding, how whitespace handling affects the value parameter, and which alphabet base64url uses. This is meaningful value beyond the schema's enumerated definitions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource combination: "Encode or decode a value across base64, base64url, hex, or URL (percent) encoding, in either direction." This unambiguously identifies the tool's operation and scope, and clearly separates it from siblings like hash_value or generate_id, which perform different transformations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear operational guidance: when to use "encode" vs "decode", and when to set outputEncoding. It also gives practical use cases like decoding base64 digests and PEM bodies. However, it does not explicitly name sibling tools or state when this tool should be preferred over them, though the context is strong enough that an agent can infer appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Mint cryptographically-random identifiers using the platform CSPRNG — the correct source for IDs that must be unpredictable, unlike model-generated values. type selects the format: uuid_v4 (random, the default), uuid_v7 (time-ordered, sortable by creation), or ulid (26-char Crockford-base32, lexicographically sortable). Set count to mint a batch in one call (up to 1000); the returned ids array always contains exactly count values and is never truncated. For uuid_v7 and ulid, a batch is monotonic — strictly increasing even within the same millisecond — so the ids array stays in sorted creation order; ids minted in the same millisecond are separated by random gaps, so no id in a batch can be derived from another. IDs from this tool feed into toolkit_generate_qr (pass ids[0] as data) to create a scannable code.
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Identifier format: uuid_v4 (random), uuid_v7 (time-ordered), or ulid (sortable Crockford-base32). | uuid_v4 |
| count | No | How many identifiers to mint (1–1000). The full batch is always returned. |
| Name | Required | Description |
|---|---|---|
| ids | No | The minted identifiers — exactly count of them, in mint order; for uuid_v7 and ulid that order is strictly increasing (sorted by creation), with random gaps between ids minted in the same millisecond. |
| type | No | The identifier format that was minted. |
| count | No | The number of identifiers minted (equals the requested count). |
| error | No | Present when the call failed. Absent on success. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, but the description goes far beyond: it discloses the source (platform CSPRNG), output guarantees ('always contains exactly count values and is never truncated'), monotonic ordering for uuid_v7/ulid, strict increasing within the same millisecond, and the security property that 'no id in a batch can be derived from another'. This rich behavioral disclosure is not present in annotations and is critical for correct use.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Each sentence earns its place: purpose and source are front-loaded, then type semantics, batch behavior, ordering guarantees, and downstream integration. There is no fluff or repetition of schema verbatim; the description is dense but well-structured, guiding the agent from conceptual purpose to invocation details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a two-parameter tool with an output schema and clear annotations, the description fully covers what an agent needs: when to use, format selection, batching limits, return-count guarantees, ordering behavior, and integration with a sibling. No critical information is missing, and the output schema handles return-shape details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds meaningful semantics beyond the schema: it explains the default (uuid_v4), clarifies each type's ordering properties, specifies 'up to 1000' for count, and introduces the guarantee that the full batch is always returned without truncation. This adds real value over the schema alone, though the schema already covers basic type and count limits.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description opens with 'Mint cryptographically-random identifiers using the platform CSPRNG' — a specific verb ('mint'), resource ('identifiers'), and method (CSPRNG). It distinguishes this tool from siblings by stating it is the correct source for unpredictable IDs and explicitly contrasts with 'model-generated values'. The purpose is unambiguous and differentiates from toolkit_hash_value, toolkit_encode_value, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description says to use this tool when IDs 'must be unpredictable' and indicates 'unlike model-generated values' — an explicit when-not. It also provides a concrete downstream workflow: 'feed into toolkit_generate_qr (pass ids[0] as data)', which acts as a usage directive. Combined with format-selection guidance for type and batching with count, the agent knows exactly when and how to invoke it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Encode text or a URL into a QR code. data is the content to encode (a link, a generated identifier such as toolkit_generate_id's ids[0], or any string). format selects the output: svg returns inline SVG markup sized in pixels, png_base64 returns base64-encoded PNG bytes (with mimeType and byteLength), and terminal returns plain Unicode half-block characters (no escape codes) for a monospace display, drawn for a dark background: light modules, quiet zone included, are blocks and dark modules are spaces. errorCorrection (L/M/Q/H) trades data capacity for damage tolerance, margin sets the quiet-zone width in modules, and scale sets pixels per module for svg and png_base64, so both are (modules + 2 × margin) × scale pixels per side. The returned version (1–40) reflects how dense the encoded data is. png_base64 rejects an image past 2048 px per side with a typed raster_too_large error, so a dense symbol needs a lower scale; svg is vector markup and carries no such limit.
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | The text or URL to encode, stored as UTF-8. Capacity is counted in bytes: 2953 UTF-8 bytes is the absolute ceiling (QR version 40, level L, byte mode). The 2953-character limit here is only an upper bound, since a non-ASCII character takes 2–4 bytes. Usable capacity drops at higher errorCorrection levels, so over-capacity data is rejected with a typed data_too_large error rather than a generic failure. | |
| scale | No | Pixels per module for svg (its width and height) and png_base64. Ignored for terminal. png_base64 also bounds the whole image at 2048 px per side, so a dense symbol or a wide margin admits a lower scale than 32 there. | |
| format | No | Output format: svg markup, png_base64 (raster bytes), or terminal (plain Unicode half-blocks, drawn for a dark background). | svg |
| margin | No | Quiet-zone width in modules around the symbol. The spec recommends 4. | |
| errorCorrection | No | Error-correction level: L (~7% recoverable) to H (~30%). Higher tolerance lowers data capacity. | M |
| Name | Required | Description |
|---|---|---|
| error | No | Present when the call failed. Absent on success. |
| format | No | The format that was produced. |
| content | No | The QR artifact: SVG markup, the terminal half-block grid (newline-separated rows), or base64 PNG bytes for png_base64. |
| version | No | QR symbol version (1–40); higher versions hold denser data and indicate denser content. |
| mimeType | No | MIME type of content for image formats. Absent for the terminal format. |
| byteLength | No | Decoded byte size of the PNG. Present only for png_base64. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint and idempotentHint annotations, the description discloses significant behavioral detail: format-specific output shapes (SVG markup, base64 PNG bytes with mimeType and byteLength, terminal Unicode blocks), typed error conditions (data_too_large, raster_too_large), the pixel-size formula, and the version range reflecting data density. It even clarifies terminal rendering for dark backgrounds. This far exceeds what annotations alone provide.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is information-dense and front-loaded with the core purpose in the first sentence. Each subsequent sentence introduces a distinct parameter or constraint, and the flow from format to error behavior is logical. It is longer than two sentences, but given the three output formats and several interacting parameters, the length is justified without wasteful repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 5 parameters, 3 formats, and a moderately complex output, the description is thorough: it covers all parameters, format-specific behaviors, encoding boundaries, and error conditions. An output schema exists, so return values are already documented. No critical information an agent needs to invoke the tool correctly is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although the schema already has 100% parameter coverage, the description adds meaningful semantics not present in the schema: how scale and margin combine into final image dimensions, which parameters are ignored by which format, how errorCorrection trades capacity against tolerance, and the pixel limit interaction with scale for png_base64. This elevates the description well above the baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource: 'Encode text or a URL into a QR code', which clearly states the tool's function. It goes beyond the title by naming concrete use cases (links, generated identifiers, strings) and enumerating the three output formats. Sibling tools like toolkit_encode_value, toolkit_generate_id, and toolkit_hash_value are clearly different in purpose, so an agent can distinguish this tool without confusion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides rich context for when to use the tool: what kinds of data are acceptable (links, identifiers, arbitrary strings), what each format yields, and how parameters interact. It does not explicitly state when not to use this tool or name alternative siblings for specific scenarios, but the sibling set is distinct enough that the usage is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Resolve a public IP address (or hostname) to geographic and network metadata: country, region, city, latitude/longitude, the owning ASN and organization, timezone, and the proxy/hosting/mobile quality flags. target accepts an IPv4/IPv6 address or a hostname — a hostname is DNS-resolved first and the resolvedIp field echoes which IP was actually located. The provider is called directly (never the target), so this is SSRF-free and safe to expose anywhere. Results are best-effort and provider-bounded: VPNs, proxies, mobile NAT, and anycast all defeat IP-to-location, accuracy is city-level at best, and many fields can be absent for reserved or thinly-documented ranges — absent fields are reported as unknown, never invented. Read proxy, hosting, and mobile before trusting the coordinates: a true on any of them means the location describes infrastructure, not the user. Private/reserved addresses have no public geolocation and are rejected. The source field names which provider answered.
| Name | Required | Description | Default |
|---|---|---|---|
| target | Yes | A public IPv4/IPv6 address or a hostname (e.g. "8.8.8.8" or "example.com"). |
| Name | Required | Description |
|---|---|---|
| asn | No | Autonomous System number, e.g. "AS15169". Absent on providers that omit it. |
| org | No | Owning organization or ISP, e.g. "Google LLC". Absent when unknown. |
| city | No | City name. Absent when unknown. |
| error | No | Present when the call failed. Absent on success. |
| proxy | No | True when the address is a known proxy, VPN, or Tor exit — the location describes the exit node, not the user. Absent when the provider does not report it. |
| mobile | No | True when the address belongs to a mobile carrier network, where NAT can place the location far from the device. Absent when unreported. |
| region | No | Region or state name. Absent when unknown. |
| source | No | The provider that answered the lookup, e.g. "ip-api". |
| target | No | The target as supplied (IP or hostname). |
| country | No | Country name. Absent when the provider does not report it. |
| hosting | No | True when the address belongs to a hosting or datacenter network, so the location is a facility rather than a person. Absent when unreported. |
| latitude | No | Latitude in decimal degrees. Absent when unknown. |
| timezone | No | IANA timezone, e.g. "America/Los_Angeles". Absent when unknown. |
| longitude | No | Longitude in decimal degrees. Absent when unknown. |
| resolvedIp | No | The IP that was actually located (a supplied hostname is resolved to this first). |
| countryCode | No | ISO 3166-1 alpha-2 country code. Absent when unknown. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With readOnlyHint=true and destructiveHint=false already in annotations, the bar is lower, yet the description still adds real context: the provider is called directly (never the target), so it is safe on untrusted input; accuracy is provider-bounded; behavior on private/reserved ranges is stated; proxy/VPN/mobile flags are defined as reliability warnings; and the source field is disclosed. Nothing contradicts the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
All four sentences are substantive and the operation is stated up front in the first sentence, with caveats and security notes after. No filler. Minor redundancy between 'accuracy is best-effort' and 'VPNs, proxies, anycast...' slightly thins the density, but nothing is wasted.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-param, read-only tool whose output is not schema-described, the description covers: the input types, DNS resolution behavior, the output fields, the meaning of proxy/mobile flags for reliability, and failure modes (private ranges rejected). An agent has everything needed to call it correctly and interpret the result.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (the single param is fully defined with three alternates: IPv4, IPv6, hostname). The description adds value beyond the schema by stating that hostnames are DNS-resolved first and that the resolved address is echoed in the response — behavior the schema cannot express. Slightly more caveat detail (e.g., punycode) would push to 5, but coverage is already high.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The first sentence states a clear verb-resource pair — resolve a public IP or hostname to a set of geographic and network metadata — and enumerates every returned field, so an agent immediately knows what it does and what it returns. It also carves out scope (public only) that distinguishes it in a toolkit whose other tools are QR, hash, and weather related.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when results are reliable and when they are not (VPNs, proxies, anycast, mobile NAT, reserved ranges), which is implicit guidance to the caller on trusting the output. It does not explicitly contrast with a sibling geolocation alternative, but the sibling set contains no competing tool, so a 4 is appropriate rather than a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate a cryptographic digest of a value, or verify a value against an expected digest. Set operation to "generate" for a digest, or "compare" to constant-time-check value against the expected digest — compare is timing-safe and avoids manual string equality checks. Omitting operation compares when expected is supplied and generates otherwise. Algorithm defaults to sha256; sha384 and sha512 are also secure, while md5 and sha1 are exposed for checksum and file-integrity compatibility ONLY and must not be used for passwords, signatures, or any security purpose. digestEncoding selects the generated digest form: lowercase hex (default), base64, or sri (-, the npm lockfile integrity and Subresource Integrity form, sha256/sha384/sha512 only). expected is accepted as hex, base64, or SRI, recognized by its shape at the algorithm's digest length, so a published checksum can be pasted as-is; an SRI value may hold several space-separated entries, as an npm integrity field can, and matches when any entry for algorithm does. inputEncoding controls how value is read before hashing (utf8 default, or hex/base64 for raw binary data) so binary blobs need no decode round-trip. The canonical use is matching a download against a vendor-published checksum or a lockfile integrity entry.
| Name | Required | Description | Default |
|---|---|---|---|
| value | Yes | The data to hash, interpreted per inputEncoding (raw text by default). | |
| expected | No | The digest to compare against, as hex (any case), standard base64, or SRI (<algorithm>-<base64>); the form is recognized from its shape at the algorithm's digest length, and a string of only hex digits is always read as hex. An SRI value may carry several space-separated entries: entries for other algorithms are skipped, and it matches when any entry for algorithm matches. Supplying it with operation omitted runs a compare; it is rejected with operation "generate". | |
| algorithm | No | Digest algorithm. sha256 (default), sha384, or sha512 for security; md5/sha1 are checksum/compat only — not for security. | sha256 |
| operation | No | "generate" produces a digest; "compare" constant-time-checks value against expected. When omitted, resolves to "compare" if expected is supplied and "generate" otherwise. | |
| inputEncoding | No | How value is decoded before hashing: utf8 text, hex, or base64. | utf8 |
| digestEncoding | No | Form of the generated digest: lowercase hex (default), standard base64, or sri (<algorithm>-<base64>, sha256/sha384/sha512 only). Applies to operation "generate". | hex |
| Name | Required | Description |
|---|---|---|
| error | No | Present when the call failed. Absent on success. |
| digest | No | Digest of value in the requested digestEncoding: lowercase hex, base64, or <algorithm>-<base64>. Present for operation "generate". |
| matches | No | Constant-time equality of the computed digest against expected. Present for operation "compare". |
| algorithm | No | The algorithm used. |
| operation | No | The operation performed, after resolving an omitted operation. |
| lengthInBytes | No | Digest size in bytes (32 for sha256, 48 for sha384, 64 for sha512, 20 for sha1, 16 for md5). Present for "generate". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as readOnly and idempotent. The description adds meaningful behavioral detail: constant-time comparison, security caveats for weak algorithms, flexible expected-format recognition, and SRI multi-entry matching. These go well beyond the annotations and give the agent a clear model of how the tool behaves without contradicting the structured metadata.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long (~150 words) but every sentence contributes a distinct piece of information: purpose, operation behavior, algorithm security, digest encoding, expected format handling, input encoding, and a canonical use case. It is front-loaded with the core purpose and then systematically covers each nuance. While it could be tightened, the density is justified by the tool's complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With an output schema present, the description need not specify return values. It thoroughly covers all parameters, their defaults, and edge cases (omitted operation, SRI multi-entries, binary input). It does not mention error conditions or limits, but these are minor given the extensive guidance and the presence of structured schemas. Overall, an agent has enough context to invoke this tool correctly in typical scenarios.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so every parameter already has a description. The tool description enriches this by explaining the interaction between operation and expected (omission logic), the shape-based recognition of expected formats, the meaning of SRI, and the rationale for inputEncoding. This adds genuine value beyond the schema's individual property descriptions, making the parameter semantics clearer and more actionable.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a precise statement of both capabilities: 'Generate a cryptographic digest of a value, or verify a value against an expected digest.' It names the verb (generate/verify), the resource (value), and clearly distinguishes the two operations. This is far from a tautology and immediately separates it from sibling tools like encode or generate_id.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides strong contextual guidance: it explains the default operation resolution, warns against using md5/sha1 for security, and gives a canonical use case ('matching a download against a vendor-published checksum or a lockfile integrity entry'). It does not explicitly name alternatives or exclusions, but the unique function makes that less critical. The 'compare is timing-safe and avoids manual string equality checks' also informs when to use this tool over manual comparison.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v2.3.1toolkit_encode_value7 fields changedInput schema / properties / operation / descriptionPrevious value: -"\"encode\" transforms text into the encoding; \"decode\" recovers text from an encoded value."New value: +"\"encode\" transforms text into the encoding; \"decode\" recovers the bytes from an encoded value."Input schema / properties / outputEncodingAdded value: +{
+ "description": "Decode only: how the recovered bytes are returned. utf8 (used when omitted) returns text and fails when the bytes are not valid UTF-8; hex and base64 return the raw bytes re-encoded, losslessly. Rejected when operation is \"encode\".",
+ "enum": [
+ "utf8",
+ "hex",
+ "base64"
+ ],
+ "type": "string"
+}Input schema / properties / value / descriptionPrevious value: -"The value to transform — raw text for encode, an encoded string for decode."New value: +"The value to transform — raw text for encode, an encoded string for decode. Whitespace is ignored when decoding hex, base64, or base64url; a url value is taken literally."Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `decode_failed`: operation is \"decode\" but value is malformed for the chosen encoding. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `decode_failed`: operation is \"decode\" but value is malformed for the chosen encoding. `decode_not_utf8`: operation is \"decode\", outputEncoding is utf8 (or omitted), and the decoded bytes are not valid UTF-8 text. `output_encoding_not_applicable`: operation is \"encode\" and outputEncoding was supplied; it selects how decoded bytes are returned. Other values are possible when a failure originates below the handler."Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[
- "decode_failed"
-]New value: +[
+ "decode_failed",
+ "decode_not_utf8",
+ "output_encoding_not_applicable"
+]Output schema / properties / outputEncodingAdded value: +{
+ "description": "How result renders the decoded bytes: utf8 text, hex, or base64. Present for operation \"decode\".",
+ "enum": [
+ "utf8",
+ "hex",
+ "base64"
+ ],
+ "type": "string"
+}Output schema / properties / result / descriptionPrevious value: -"The transformed value (encoded text, or the decoded original)."New value: +"The transformed value: encoded text for encode; for decode, the recovered bytes as UTF-8 text, hex, or base64 per outputEncoding."toolkit_generate_id1 field changedOutput schema / properties / ids / descriptionPrevious value: -"The minted identifiers — exactly count of them, in mint order; for uuid_v7 and ulid that order is strictly increasing (sorted by creation)."New value: +"The minted identifiers — exactly count of them, in mint order; for uuid_v7 and ulid that order is strictly increasing (sorted by creation), with random gaps between ids minted in the same millisecond."toolkit_generate_qr4 fields changedInput schema / properties / data / descriptionPrevious value: -"The text or URL to encode. 2953 is the absolute ceiling (QR version 40, level L, byte mode); usable capacity drops at higher errorCorrection levels, so over-capacity data is rejected with a typed data_too_large error rather than a generic failure."New value: +"The text or URL to encode, stored as UTF-8. Capacity is counted in bytes: 2953 UTF-8 bytes is the absolute ceiling (QR version 40, level L, byte mode). The 2953-character limit here is only an upper bound, since a non-ASCII character takes 2–4 bytes. Usable capacity drops at higher errorCorrection levels, so over-capacity data is rejected with a typed data_too_large error rather than a generic failure."Input schema / properties / format / descriptionPrevious value: -"Output format: svg markup, png_base64 (raster bytes), or a terminal-renderable string."New value: +"Output format: svg markup, png_base64 (raster bytes), or terminal (plain Unicode half-blocks, drawn for a dark background)."Input schema / properties / scale / descriptionPrevious value: -"Pixels per module for raster (png_base64) output. Ignored for terminal. png_base64 also bounds the whole image at 2048 px per side, so a dense symbol or a wide margin admits a lower scale than 32."New value: +"Pixels per module for svg (its width and height) and png_base64. Ignored for terminal. png_base64 also bounds the whole image at 2048 px per side, so a dense symbol or a wide margin admits a lower scale than 32 there."Output schema / properties / content / descriptionPrevious value: -"The QR artifact: SVG markup, a terminal-renderable string, or base64 PNG bytes for png_base64."New value: +"The QR artifact: SVG markup, the terminal half-block grid (newline-separated rows), or base64 PNG bytes for png_base64."toolkit_hash_value13 fields changedInput schema / properties / algorithm / descriptionPrevious value: -"Digest algorithm. sha256 (default) or sha512 for security; md5/sha1 are checksum/compat only — not for security."New value: +"Digest algorithm. sha256 (default), sha384, or sha512 for security; md5/sha1 are checksum/compat only — not for security."Input schema / properties / algorithm / enumPrevious value: -[
- "sha256",
- "sha512",
- "sha1",
- "md5"
-]New value: +[
+ "sha256",
+ "sha384",
+ "sha512",
+ "sha1",
+ "md5"
+]Input schema / properties / digestEncodingAdded value: +{
+ "default": "hex",
+ "description": "Form of the generated digest: lowercase hex (default), standard base64, or sri (<algorithm>-<base64>, sha256/sha384/sha512 only). Applies to operation \"generate\".",
+ "enum": [
+ "hex",
+ "base64",
+ "sri"
+ ],
+ "type": "string"
+}Input schema / properties / expected / descriptionPrevious value: -"The expected lowercase-hex digest to compare against. Required when operation is \"compare\"."New value: +"The digest to compare against, as hex (any case), standard base64, or SRI (<algorithm>-<base64>); the form is recognized from its shape at the algorithm's digest length, and a string of only hex digits is always read as hex. An SRI value may carry several space-separated entries: entries for other algorithms are skipped, and it matches when any entry for algorithm matches. Supplying it with operation omitted runs a compare; it is rejected with operation \"generate\"."Input schema / properties / inputEncoding / descriptionPrevious value: -"How value (and expected's pre-image, when relevant) is decoded before hashing: utf8 text, hex, or base64."New value: +"How value is decoded before hashing: utf8 text, hex, or base64."Input schema / properties / operation / defaultRemoved value: -"generate"Input schema / properties / operation / descriptionPrevious value: -"\"generate\" produces a digest; \"compare\" constant-time-checks value against expected."New value: +"\"generate\" produces a digest; \"compare\" constant-time-checks value against expected. When omitted, resolves to \"compare\" if expected is supplied and \"generate\" otherwise."Output schema / properties / algorithm / enumPrevious value: -[
- "sha256",
- "sha512",
- "sha1",
- "md5"
-]New value: +[
+ "sha256",
+ "sha384",
+ "sha512",
+ "sha1",
+ "md5"
+]Output schema / properties / digest / descriptionPrevious value: -"Lowercase-hex digest of value. Present for operation \"generate\"."New value: +"Digest of value in the requested digestEncoding: lowercase hex, base64, or <algorithm>-<base64>. Present for operation \"generate\"."Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `missing_expected`: operation is \"compare\" but no expected digest was supplied. `expected_length_mismatch`: The expected digest length does not match the algorithm, so compare would always fail. `invalid_input_encoding`: value is not valid for the declared inputEncoding (e.g. non-hex characters with inputEncoding \"hex\"). Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `missing_expected`: operation is \"compare\" but no expected digest was supplied. `expected_without_compare`: operation is \"generate\" but an expected digest was also supplied, so it would be ignored. `expected_malformed`: expected is not a hex, standard base64, or sha256/sha384/sha512 SRI digest, or an SRI value holds a token that is not an SRI entry. `expected_length_mismatch`: expected is a recognized digest form but its length does not match the algorithm, so compare would always fail. `expected_algorithm_mismatch`: expected is SRI and none of its entries names the chosen algorithm. `sri_unsupported_algorithm`: digestEncoding is \"sri\" and algorithm is md5 or sha1, which SRI does not define. `invalid_input_encoding`: value is not valid for the declared inputEncoding (e.g. non-hex characters with inputEncoding \"hex\"). Other values are possible when a failure originates below the handler."Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[
- "missing_expected",
- "expected_length_mismatch",
- "invalid_input_encoding"
-]New value: +[
+ "missing_expected",
+ "expected_without_compare",
+ "expected_malformed",
+ "expected_length_mismatch",
+ "expected_algorithm_mismatch",
+ "sri_unsupported_algorithm",
+ "invalid_input_encoding"
+]Output schema / properties / lengthInBytes / descriptionPrevious value: -"Digest size in bytes (32 for sha256, 64 for sha512, 20 for sha1, 16 for md5). Present for \"generate\"."New value: +"Digest size in bytes (32 for sha256, 48 for sha384, 64 for sha512, 20 for sha1, 16 for md5). Present for \"generate\"."Output schema / properties / operation / descriptionPrevious value: -"The operation performed."New value: +"The operation performed, after resolving an omitted operation."v2.2.2toolkit_encode_value6 fields changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesAdded value: +falseOutput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Output schema / anyOfAdded value: +[
+ {
+ "not": {
+ "required": [
+ "error"
+ ]
+ },
+ "required": [
+ "encoding",
+ "operation",
+ "result"
+ ]
+ },
+ {
+ "required": [
+ "error"
+ ]
+ }
+]Output schema / properties / errorAdded value: +{
+ "additionalProperties": {},
+ "description": "Present when the call failed. Absent on success.",
+ "properties": {
+ "code": {
+ "description": "JSON-RPC error code for this failure.",
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ },
+ "data": {
+ "additionalProperties": {},
+ "properties": {
+ "reason": {
+ "description": "Machine-readable failure mode. Declared by this tool: `decode_failed`: operation is \"decode\" but value is malformed for the chosen encoding. Other values are possible when a failure originates below the handler.",
+ "examples": [
+ "decode_failed"
+ ],
+ "type": "string"
+ },
+ "recovery": {
+ "additionalProperties": {},
+ "description": "Actionable next step for the caller.",
+ "properties": {
+ "hint": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "hint"
+ ],
+ "type": "object"
+ },
+ "retryable": {
+ "description": "Whether retrying may succeed.",
+ "type": "boolean"
+ }
+ },
+ "type": "object"
+ },
+ "message": {
+ "description": "Human-readable description of what went wrong.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "code",
+ "message"
+ ],
+ "type": "object"
+}Output schema / requiredRemoved value: -[
- "encoding",
- "operation",
- "result"
-]toolkit_generate_id6 fields changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesAdded value: +falseOutput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Output schema / anyOfAdded value: +[
+ {
+ "not": {
+ "required": [
+ "error"
+ ]
+ },
+ "required": [
+ "type",
+ "ids",
+ "count"
+ ]
+ },
+ {
+ "required": [
+ "error"
+ ]
+ }
+]Output schema / properties / errorAdded value: +{
+ "additionalProperties": {},
+ "description": "Present when the call failed. Absent on success.",
+ "properties": {
+ "code": {
+ "description": "JSON-RPC error code for this failure.",
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ },
+ "data": {
+ "additionalProperties": {},
+ "properties": {
+ "reason": {
+ "description": "Machine-readable failure mode.",
+ "type": "string"
+ },
+ "recovery": {
+ "additionalProperties": {},
+ "description": "Actionable next step for the caller.",
+ "properties": {
+ "hint": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "hint"
+ ],
+ "type": "object"
+ },
+ "retryable": {
+ "description": "Whether retrying may succeed.",
+ "type": "boolean"
+ }
+ },
+ "type": "object"
+ },
+ "message": {
+ "description": "Human-readable description of what went wrong.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "code",
+ "message"
+ ],
+ "type": "object"
+}Output schema / requiredRemoved value: -[
- "type",
- "ids",
- "count"
-]toolkit_generate_qr6 fields changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesAdded value: +falseOutput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Output schema / anyOfAdded value: +[
+ {
+ "not": {
+ "required": [
+ "error"
+ ]
+ },
+ "required": [
+ "format",
+ "content",
+ "version"
+ ]
+ },
+ {
+ "required": [
+ "error"
+ ]
+ }
+]Output schema / properties / errorAdded value: +{
+ "additionalProperties": {},
+ "description": "Present when the call failed. Absent on success.",
+ "properties": {
+ "code": {
+ "description": "JSON-RPC error code for this failure.",
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ },
+ "data": {
+ "additionalProperties": {},
+ "properties": {
+ "reason": {
+ "description": "Machine-readable failure mode. Declared by this tool: `data_too_large`: data exceeds the QR capacity for the chosen errorCorrection level and encoding mode. `raster_too_large`: format is png_base64 and (modules + 2 × margin) × scale exceeds the pixel budget. Other values are possible when a failure originates below the handler.",
+ "examples": [
+ "data_too_large",
+ "raster_too_large"
+ ],
+ "type": "string"
+ },
+ "recovery": {
+ "additionalProperties": {},
+ "description": "Actionable next step for the caller.",
+ "properties": {
+ "hint": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "hint"
+ ],
+ "type": "object"
+ },
+ "retryable": {
+ "description": "Whether retrying may succeed.",
+ "type": "boolean"
+ }
+ },
+ "type": "object"
+ },
+ "message": {
+ "description": "Human-readable description of what went wrong.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "code",
+ "message"
+ ],
+ "type": "object"
+}Output schema / requiredRemoved value: -[
- "format",
- "content",
- "version"
-]toolkit_geolocate_ip6 fields changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesAdded value: +falseOutput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Output schema / anyOfAdded value: +[
+ {
+ "not": {
+ "required": [
+ "error"
+ ]
+ },
+ "required": [
+ "target",
+ "resolvedIp",
+ "source"
+ ]
+ },
+ {
+ "required": [
+ "error"
+ ]
+ }
+]Output schema / properties / errorAdded value: +{
+ "additionalProperties": {},
+ "description": "Present when the call failed. Absent on success.",
+ "properties": {
+ "code": {
+ "description": "JSON-RPC error code for this failure.",
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ },
+ "data": {
+ "additionalProperties": {},
+ "properties": {
+ "reason": {
+ "description": "Machine-readable failure mode. Declared by this tool: `unresolvable_host`: A hostname target failed DNS resolution. `private_target`: The target resolves to a private/reserved IP with no public geolocation. Other values are possible when a failure originates below the handler.",
+ "examples": [
+ "unresolvable_host",
+ "private_target"
+ ],
+ "type": "string"
+ },
+ "recovery": {
+ "additionalProperties": {},
+ "description": "Actionable next step for the caller.",
+ "properties": {
+ "hint": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "hint"
+ ],
+ "type": "object"
+ },
+ "retryable": {
+ "description": "Whether retrying may succeed.",
+ "type": "boolean"
+ }
+ },
+ "type": "object"
+ },
+ "message": {
+ "description": "Human-readable description of what went wrong.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "code",
+ "message"
+ ],
+ "type": "object"
+}Output schema / requiredRemoved value: -[
- "target",
- "resolvedIp",
- "source"
-]toolkit_hash_value6 fields changedInput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Input schema / additionalPropertiesAdded value: +falseOutput schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Output schema / anyOfAdded value: +[
+ {
+ "not": {
+ "required": [
+ "error"
+ ]
+ },
+ "required": [
+ "algorithm",
+ "operation"
+ ]
+ },
+ {
+ "required": [
+ "error"
+ ]
+ }
+]Output schema / properties / errorAdded value: +{
+ "additionalProperties": {},
+ "description": "Present when the call failed. Absent on success.",
+ "properties": {
+ "code": {
+ "description": "JSON-RPC error code for this failure.",
+ "maximum": 9007199254740991,
+ "minimum": -9007199254740991,
+ "type": "integer"
+ },
+ "data": {
+ "additionalProperties": {},
+ "properties": {
+ "reason": {
+ "description": "Machine-readable failure mode. Declared by this tool: `missing_expected`: operation is \"compare\" but no expected digest was supplied. `expected_length_mismatch`: The expected digest length does not match the algorithm, so compare would always fail. `invalid_input_encoding`: value is not valid for the declared inputEncoding (e.g. non-hex characters with inputEncoding \"hex\"). Other values are possible when a failure originates below the handler.",
+ "examples": [
+ "missing_expected",
+ "expected_length_mismatch",
+ "invalid_input_encoding"
+ ],
+ "type": "string"
+ },
+ "recovery": {
+ "additionalProperties": {},
+ "description": "Actionable next step for the caller.",
+ "properties": {
+ "hint": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "hint"
+ ],
+ "type": "object"
+ },
+ "retryable": {
+ "description": "Whether retrying may succeed.",
+ "type": "boolean"
+ }
+ },
+ "type": "object"
+ },
+ "message": {
+ "description": "Human-readable description of what went wrong.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "code",
+ "message"
+ ],
+ "type": "object"
+}Output schema / requiredRemoved value: -[
- "algorithm",
- "operation"
-]v2.2.0toolkit_generate_qr1 field changedInput schema / properties / scale / descriptionPrevious value: -"Pixels per module for raster (png_base64) output. Ignored for terminal."New value: +"Pixels per module for raster (png_base64) output. Ignored for terminal. png_base64 also bounds the whole image at 2048 px per side, so a dense symbol or a wide margin admits a lower scale than 32."toolkit_geolocate_ip10 fields changedOutput schema / properties / asn / maxLengthAdded value: +256Output schema / properties / city / maxLengthAdded value: +256Output schema / properties / country / maxLengthAdded value: +256Output schema / properties / countryCode / maxLengthAdded value: +256Output schema / properties / hostingAdded value: +{
+ "description": "True when the address belongs to a hosting or datacenter network, so the location is a facility rather than a person. Absent when unreported.",
+ "type": "boolean"
+}Output schema / properties / mobileAdded value: +{
+ "description": "True when the address belongs to a mobile carrier network, where NAT can place the location far from the device. Absent when unreported.",
+ "type": "boolean"
+}Output schema / properties / org / maxLengthAdded value: +256Output schema / properties / proxyAdded value: +{
+ "description": "True when the address is a known proxy, VPN, or Tor exit — the location describes the exit node, not the user. Absent when the provider does not report it.",
+ "type": "boolean"
+}Output schema / properties / region / maxLengthAdded value: +256Output schema / properties / timezone / maxLengthAdded value: +256v2.0.1toolkit_generate_id1 field changedOutput schema / properties / ids / descriptionPrevious value: -"The minted identifiers — exactly count of them, in mint order."New value: +"The minted identifiers — exactly count of them, in mint order; for uuid_v7 and ulid that order is strictly increasing (sorted by creation)."toolkit_generate_qr1 field changedInput schema / properties / data / descriptionPrevious value: -"The text or URL to encode. Capped at 2953 bytes — the absolute QR capacity (version 40, level L)."New value: +"The text or URL to encode. 2953 is the absolute ceiling (QR version 40, level L, byte mode); usable capacity drops at higher errorCorrection levels, so over-capacity data is rejected with a typed data_too_large error rather than a generic failure."v2.0.0checkConnectivityclearGeoCachecompareHashesconvertTimezonegenerateQRCodegenerateUUIDgeolocategetCurrentTimegetLoadAveragegetNetworkInterfacesgetPublicIPgetSystemInfohashDatalistTimezonespingHosttoolkit_encode_valuetoolkit_generate_idtoolkit_generate_qrtoolkit_geolocate_iptoolkit_hash_valuetraceroutecheckConnectivityclearGeoCachecompareHashesconvertTimezonegenerateQRCodegenerateUUIDgeolocategetCurrentTimegetLoadAveragegetNetworkInterfacesgetPublicIPgetSystemInfohashDatalistTimezonespingHosttracerouteScored across 5 tools
Each tool serves a clearly distinct purpose: QR generation, hashing, ID generation, encoding/decoding, and IP geolocation. There is no overlap or possibility of confusion between tools. Descriptions are detailed and unambiguous.
All tools use the consistent 'toolkit_' prefix with snake_case names following a verb_noun pattern (generate_qr, hash_value, generate_id, encode_value, geolocate_ip). The naming is predictable and uniform across the entire set.
With 5 tools, the server is well-scoped for a general-purpose toolkit. Each tool is substantial and earns its place, covering a broad range of utility functions without redundancy. The count is neither thin nor bloated.
The toolkit covers a solid variety of utility categories (generation, hashing, encoding, geolocation), but lacks common text/data manipulation features like string transformation or JSON handling. The core workflows within each tool are complete, with no dead ends, though the breadth could be broader for a general toolkit.
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Real-time planetary signal engine and Model Context Protocol (MCP) server for autonomous AI agents.
MCP server for Pentest-Tools.com: run scans, manage findings and reports via your preffered LLM.
