MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
A skill your agent uses when writing ida-domain scripts, querying .i64 databases, or analyzing binaries.
$ npx skills add TsingShui/ida-agent-bridge --skill ida-agent-bridge -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install TsingShui/ida-agent-bridge ida-agent-bridge --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ida-agent-bridge" agent skill from https://github.com/TsingShui/ida-agent-bridge/tree/main into .claude/skills/ida-agent-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ida-agent-bridge", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add TsingShui/ida-agent-bridge --skill ida-agent-bridge -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install TsingShui/ida-agent-bridge ida-agent-bridge --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ida-agent-bridge" agent skill from https://github.com/TsingShui/ida-agent-bridge/tree/main into .agents/skills/ida-agent-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ida-agent-bridge", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add TsingShui/ida-agent-bridge --skill ida-agent-bridge -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install TsingShui/ida-agent-bridge ida-agent-bridge --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ida-agent-bridge" agent skill from https://github.com/TsingShui/ida-agent-bridge/tree/main into .cursor/skills/ida-agent-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ida-agent-bridge", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add TsingShui/ida-agent-bridge --skill ida-agent-bridge -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install TsingShui/ida-agent-bridge ida-agent-bridge --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ida-agent-bridge" agent skill from https://github.com/TsingShui/ida-agent-bridge/tree/main into .gemini/skills/ida-agent-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ida-agent-bridge", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install TsingShui/ida-agent-bridge ida-agent-bridgeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add TsingShui/ida-agent-bridge --skill ida-agent-bridge -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ida-agent-bridge" agent skill from https://github.com/TsingShui/ida-agent-bridge/tree/main into .github/skills/ida-agent-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ida-agent-bridge", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add TsingShui/ida-agent-bridge --skill ida-agent-bridge -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install TsingShui/ida-agent-bridge ida-agent-bridge --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ida-agent-bridge" agent skill from https://github.com/TsingShui/ida-agent-bridge/tree/main into .opencode/skills/ida-agent-bridge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ida-agent-bridge", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
ida-agent-bridgeA skill your agent uses when writing ida-domain scripts, querying .i64 databases, or analyzing binaries.
Ida Agent Bridge is an agent skill from TsingShui/ida-agent-bridge. Use when writing ida-domain scripts, querying .i64 databases, or analyzing binaries. Provides short-connection REPL commands (disasm, xrefs, hexdump, pseudocode, rename) and arbitrary Python script execution piped via nc, with real-time file sync on rename/comment/patch.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 44 other files (for example `README.en.md`, `README.md` and `reference/ida-domain-advanced.md`).
It works with Python. The repository describes itself as: A CLI-first, headless, AI-native IDA Pro bridge built on Unix philosophy. The licence is MIT.
2 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 016b928. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships script files (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Ida Agent Bridge loads about 1.7k tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 125 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from TsingShui/ida-agent-bridge at commit 016b928, republished under its MIT licence (© TsingShui). 125 words, ~1,709 tokens.
.claude/skills/ida-agent-bridge/SKILL.md (or your agent's skills folder). This skill also uses 40 other files; get the full folder from GitHub.首先执行 ps 确认现有进程:
ps -ef | grep ida-bridge | grep -v grep根据结果判断:
没有发现正在运行的 ida-bridge。请告诉我:
- 要分析的文件路径(
.i64/.so)- 需要我帮你启动吗?
用户确认启动后:
ida-bridge /path/to/file.i64 <port> --skip-export &--skip-export,不做全量导出(速度更快)这个任务可能需要导出函数索引,是否启用导出?(首次较慢)
启动后用 !ping 确认就绪。
Agent 只使用短连接模式。
--human-shell是给人用的交互模式,Agent 不应使用。
优先级:REPL 指令 → Python 脚本 → 原生 ida_ 模块*
REPL 快捷指令(echo '!cmd' | nc localhost PORT)
↓ 指令无法满足(批量操作/复杂逻辑)
Python 脚本(cat script.py | nc localhost PORT)
↓ ida-domain 没有封装
原生 ida_* 模块(直接在脚本中调用)不需要写 Python,直接发单行命令。这是最快的操作方式。
地址和函数名均可互换(0x... 十六进制地址或符号名)。
echo '!afl' | nc localhost <port> # 列出所有函数
echo '!afl jni' | nc localhost <port> # 搜含 jni 的函数名
echo '!afi main' | nc localhost <port> # 函数详情
echo '!iz ssl' | nc localhost <port> # 搜含 ssl 的字符串
echo '!axi malloc' | nc localhost <port> # 导入符号的所有调用点输出格式:
# !afl — TAB 分隔: 地址 名称 大小(hex) callers=N
0x11f0 _ossl_fnv1a_hash 0x38 callers=0
0x1228 _ossl_ctype_check 0x28 callers=2
# !afi — 键值对
name: _ossl_fnv1a_hash
addr: 0x11f0 - 0x1228
size: 0x38 (56)
callers: 0
callees: 0
# !iz — 地址 内容 refs=N [引用函数]
0x810ee ossltest refs=1 [_alpn_select_cb]
# !axi — 地址 引用类型 [所在函数]
0x12f0 CALL_NEAR [in: _SSL_read]echo '!axt 0x1234' | nc localhost <port> # xrefs to 地址
echo '!axf main' | nc localhost <port> # xrefs from 函数名输出格式:
# !axt / !axf — 地址 引用类型 [所在函数]
0x2f020 CALL_NEAR [in: _ossl_qlog_set_filter]
0x2f064 CALL_NEAR [in: _ossl_qlog_set_filter]echo '!pd 0x1234' | nc localhost <port> # 从地址反汇编 16 条(默认)
echo '!pd 0x1234 32' | nc localhost <port> # 反汇编 32 条
echo '!pdf main' | nc localhost <port> # 整函数反汇编(带 CFG block 标注)
echo '!pdc 0x1234' | nc localhost <port> # 伪代码
echo '!pdc 0x1234 -s' | nc localhost <port> # 过滤变量声明(大函数用)
echo '!mc main' | nc localhost <port> # 微码(默认 generated)
echo '!mc main lvars' | nc localhost <port> # 微码 maturity: generated/preopt/locopt/calls/glbopt1/glbopt2/glbopt3/lvars
echo '!deps main' | nc localhost <port> # 递归调用链(默认深度 3)
echo '!deps main 5' | nc localhost <port> # 调用链深度 5输出格式:
# !pd — 地址 指令助记符 操作数
0x11f0 MOV X8, X0
0x11f4 MOV X0, #0xCBF29CE484222325
# !pdf — 带 CFG block 标注的反汇编
; block 0 [0x11f0 - 0x1208]
0x11f0 MOV X8, X0
0x1204 CBZ X1, locret_1224 ; true→ 0x1224 false→ 0x1208
; block 1 [0x1208 - 0x1210]
0x1208 MOV X9, #0x100000001B3 ; → 0x1210
# !pdc — C 伪代码,首行注释标注函数名和地址
; _ossl_fnv1a_hash @ 0x11f0
__int64 __fastcall ossl_fnv1a_hash(unsigned __int8 *a1, __int64 a2)
{
...
}
# !deps — 缩进树形调用链
_ossl_isdigit [0x1250]
_ossl_ctype_check [0x1228]echo '!afn 0x1234 sign_request' | nc localhost <port> # 重命名函数(自动同步导出,caller 级联刷新)
echo '!cc main entry point' | nc localhost <port> # 设置函数级注释(Function Comment)
echo '!ca 0x1234 key check here' | nc localhost <port> # 设置地址级注释(Address Comment)echo '!sb 01 14 40 f9' | nc localhost <port> # 搜索字节序列(全局)
echo '!sb 01 14 40 f9 0x1000 0x5000' | nc localhost <port> # 限定地址范围搜索
echo '!hd 0x1234' | nc localhost <port> # hexdump 64 字节(默认)
echo '!hd 0x1234 128' | nc localhost <port> # hexdump 128 字节
echo '!hd func_name' | nc localhost <port> # 符号名同样支持
echo '!ping' | nc localhost <port> # 探活,返回打开的文件路径
echo '!pwd' | nc localhost <port> # 当前工作目录
echo '!quit' | nc localhost <port> # 关闭服务输出格式:
# !sb — 地址 函数名+偏移 [所在函数]
0x2e00 _ssl_ctrl+0x20 [in: _ssl_ctrl]
0x3a1f _dtls1_start_timer+0x43 [in: _dtls1_start_timer]
# !hd — 地址 hex bytes ASCII
0x11f0 e8 03 00 aa a0 64 84 d2 40 84 b0 f2 80 9c d3 f2 .....d..@.......
# !ping — 返回当前打开的文件绝对路径
/path/to/libssl.dylibREPL 输出是纯文本,可直接接 grep、sort、awk、jq 等工具处理,无需额外解析。
# 找被调用最多的函数
echo '!afl' | nc localhost <port> | sort -t= -k2 -rn | head -10
# 找所有大于 0x200 字节的未命名函数
echo '!afl' | nc localhost <port> | awk -F'\t' '$3 >= 0x200 && $2 ~ /^sub_/'
# 从伪代码提取所有被调用函数名
echo '!pdc _wpacket_intern_close' | nc localhost <port> | grep -oP '\b\w+(?=\()' | sort -u
# 找包含特定字符串的函数(先搜字符串,再查引用)
ADDR=$(echo '!iz encrypt' | nc localhost <port> | awk 'NR==1{print $1}')
echo "!axt $ADDR" | nc localhost <port>
# 批量对所有 JNI 函数生成伪代码并保存
echo '!afl jni' | nc localhost <port> | awk '{print $1}' | while read addr; do
echo "!pdc $addr" | nc localhost <port> > "/tmp/pdc_${addr}.c"
done指令不够用时才写脚本。db 已预注入,无需 import。
导出目录结构(启动时指定的 <export_dir>,默认 ./ida-bridge-<文件名>/):
<export_dir>/
├── decompile/ <name>.c — 每个函数的 Hex-Rays 伪代码
├── strings.tsv addr\tencoding\tcontents
├── imports.tsv addr\tmodule\tname
├── exports.tsv addr\tname
├── function_index.tsv addr\tname\tlogic_lines\tbranch_density\tcall_density\tstring_density\topaque_density\ttotal_insns\tbitop_density\txor_density\tcaller_count\tfile\tcallers\tcallees
├── hash_index.json 函数地址→CRC32 hash,增量导出用
└── export_config.json 导出配置(compute_metrics 等)cat my_script.py | nc localhost <port>典型脚本模式:
# 批量重命名(hooks 自动同步导出)
for func in db.functions.get_all():
name = db.functions.get_name(func)
if name.startswith("sub_") and func.end_ea - func.start_ea > 0x200:
print(hex(func.start_ea), name)
db.names.set_name(0x12AB, 'sign_request')写脚本前必须先读对应 API 文档:
${CLAUDE_SKILL_DIR}/reference/ida-domain.md — 日常必用 API(函数、名称、字节、xrefs、指令、字符串、导入、类型、伪代码基础、微码基础)。覆盖 ~90% 场景。${CLAUDE_SKILL_DIR}/reference/ida-domain-advanced.md — Pseudocode CTree 深层操作和 Microcode 修改/分析的高级 API。不确定 API 用法时,先 Read 文档,不要在 REPL 里试探。
ida-domain 做不到的降级到原生 ida_* 模块。ida-domain 对象可直接传给原生 SDK 函数。
| Avoid | Do Instead |
|---|---|
idc.* functions | Use ida_* modules |
| Hardcoded addresses | Use names, patterns, or xrefs |
© TsingShui, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 40 other files in the repository root of TsingShui/ida-agent-bridge.
Open the folder on GitHubat commit 016b928
Ida Agent Bridge next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Ida Agent Bridge this skillTsingShui/ida-agent-bridge | 109 | — | ~1.7k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| PDF Processinganthropics/skills | 180k | 47 repos | ~2k | Automated safety check: Pass | Proprietary | |
| NotebookLM Research AssistantPleasePrompto/notebooklm-skill | 7.8k | 14 repos | ~2.4k | Automated safety check: Notes | MIT | |
| Manim Video Productionbrowser-use/video-use | 29k | 6 repos | ~3k | Automated safety check: Pass | MIT | |
| PPT Masterhugohe3/ppt-master | 59k | 1 repos | ~2.5k | Automated safety check: Pass | MIT |
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
anthropics/skills
Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR.
PleasePrompto/notebooklm-skill
Lets Claude Code ask questions of your Google NotebookLM notebooks through browser automation and return answers grounded in your uploaded sources.
browser-use/video-use
Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories.
hugohe3/ppt-master
Generates editable PowerPoint decks, rebuilds slides from images, fills .pptx templates and polishes existing presentations through routed workflows.
zLanqing/codex-claude-academic-skills
Machine learning in Python with scikit-learn. An agent skill from zLanqing/codex-claude-academic-skills.
Works with
A skill your agent uses when writing ida-domain scripts, querying .i64 databases, or analyzing binaries. Ida Agent Bridge is an agent skill from TsingShui/ida-agent-bridge.i64 databases, or analyzing binaries.
Ida Agent Bridge fits situations like: writing ida-domain scripts; querying .i64 databases; analyzing binaries.
Run `npx skills add TsingShui/ida-agent-bridge --skill ida-agent-bridge -a claude-code`. Or copy the skill folder (the TsingShui/ida-agent-bridge repository) into .claude/skills/ida-agent-bridge in your project. Claude Code loads it when a task matches its description.
Run `npx skills add TsingShui/ida-agent-bridge --skill ida-agent-bridge -a codex`. Or copy the skill folder (the TsingShui/ida-agent-bridge repository) into .agents/skills/ida-agent-bridge in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add TsingShui/ida-agent-bridge --skill ida-agent-bridge -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ida-agent-bridge, .gemini/skills/ida-agent-bridge, .github/skills/ida-agent-bridge and .opencode/skills/ida-agent-bridge in your project.
Going by SKILL.md and its folder, Ida Agent Bridge needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Ida Agent Bridge is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Ida Agent Bridge: MCP Server Builder (anthropics/skills, 180k stars), PDF Processing (anthropics/skills, 180k stars), NotebookLM Research Assistant (PleasePrompto/notebooklm-skill, 7.8k stars) and Manim Video Production (browser-use/video-use, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
TsingShui (a GitHub user) maintains it in TsingShui/ida-agent-bridge, which has 109 GitHub stars. The repository was last updated on May 15, 2026.
Source: TsingShui/ida-agent-bridge on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.