Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add nguyenthdat/burp-mcp --skill burpsuitegit clone --depth 1 https://github.com/nguyenthdat/burp-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nguyenthdat/burp-mcp/burpsuite)<a href="https://agentmods.dev/skills/nguyenthdat/burp-mcp/burpsuite"><img src="https://agentmods.dev/badge/skills/nguyenthdat/burp-mcp/burpsuite/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nguyenthdat/burp-mcp/burpsuite"><img src="https://agentmods.dev/badge/skills/nguyenthdat/burp-mcp/burpsuite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00168 | $0.03830 |
| Opus 5.5 | $0.00067 | $0.01532 |
| Sonnet 5.5 | $0.00034 | $0.00766 |
| Haiku 4.5 | $0.00017 | $0.00383 |
Grade A, and why
burpsuite scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Export requests to `curl` or Python `requests` using `burp_http` action `export`. How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Burp Suite Security Testing Skill
Use the native burp-mcp server as a controlled, deterministic interface to Burp Suite. Focus on reproducible security evidence, defensive test isolation, and bounded side effects.
Tool names in this skill are server-local names. Use the exact names returned by the connected server's tools/list; MCP hosts may expose qualified bindings such as mcp__burp_mcp_burp_http or tool.mcp__burp_mcp_burp_http, so do not assume tool.burp_http exists in an eval kernel. The runtime MCP schema is authoritative.
Decision Index: When to Load Specific References
Load supporting reference files only when the task enters a specific domain:
| Domain / Task | Reference to Load | Purpose |
|---|---|---|
| AppSec Testing Methodologies & OAST | references/appsec-testing-guide.md |
OWASP WSTG testing techniques for Auth, IDOR, SQLi, XSS, OAST (Collaborator blind SSRF/RCE/XXE/SQLi), Race conditions, and WebSockets. |
| Complete Tool Schema & Inputs | references/tool-catalog.md |
Parameter lists, constraints, and schemas for the current tool runtime. |
| PortSwigger Desktop Workflows | references/burp-workflows.md |
Standard desktop workflows for Proxy, Scope, Repeater, Intruder, and Scanner. |
| Graph-Based Attack Surface | references/sitegraph.md |
SQLite sitegraph partitioning, modes, clustering, shortest path, and impact analysis. |
| Scanner Custom Checks | references/bcheck-authoring.md |
Writing, reviewing, validating, and importing declarative BCheck scripts. |
| Table Filters & Java Scripts | references/bambda-authoring.md |
Writing, reviewing, and importing Java Bambda scripts for Proxy, Logger, and Repeater. |
Safety Contract & Testing Discipline
- Verify Authorization: Identify the exact target scheme, host, port, and allowed path boundaries before sending active traffic, fuzzing, crawling, polling Collaborator, or modifying Burp state. Scope is a routing boundary, not legal authorization.
- Token Efficiency First: Prefer compact metadata history and details (
burp_proxy/burp_loggerdefaultinclude_bodies: false,max_body_length: 4096default). Use server-side projection (headers_only,extract_json: "$.data...",extract_css: "form#login") or explicit capped bodies (include_bodies: true) to preserve client context window. Projections use bounded custom Pest parsers (extract_csswith structural/logical pseudos, sibling/child combinators, and:contains;extract_jsonwith negative indexes, slices, recursive descent, and logical filter expressions). Original byte lengths and truncation state are emitted. SiteGraph passive enrichment is separate: its embedded2026.09.05typed TOML pack contains 105 ordinary regex rules evaluated by surface-partitioned byte-safeRegexSetmatching. - Start Read-Only: Prefer Proxy history (
burp_proxyactionhistory), Logger traffic (burp_loggeractionquery), Target site map (burp_targetactionsitemap), target info (burp_targetactioninfo), Scanner issues (burp_scanneractionlist_issues), sitegraph queries (sitegraphactionsearch), and offline decoder operations (decoder) before generating active traffic. - Preserve Operator State: Record every temporary scope addition, intercept state change, HTTP handler, proxy rule, session rule, macro, cookie, background job, and managed WebSocket connection. Restore or remove it during cleanup.
- Interception Discipline: Do not enable proxy interception in unattended flows. Both MCP HTTP (
burp_intercept_controller) and WebSocket (burp_websocket_intercept_controller) controllers require a narrowurl_filterorin_scope_only: true; both default to RECEIVED-only pauses (preventing duplicate TO_BE_SENT pauses). One logical HTTP exchange may yield request and response items, and one bidirectional WebSocket exchange yields outbound and inbound messages; clients must resolve all intended items, verify pending is zero, and disable the controller. Restore original operator state upon completion. - Rate & Concurrency Bounds: Limit parallel requests (at most 32 via
burp_httpactionsend_batch), cap scan concurrency via custom resource pools (burp_scan_configactionupsert_pool), and pace background job polling. - Protect Secrets & Redact Evidence: Never log or disclose private keys, session cookies, auth tokens, or Collaborator secrets in reports.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +12 lines 609447b1c43c
- 1mo ago First seen · 145 lines · 168 tokens per session scan A abae6fbcf913
burpsuite is a skill published in the GitHub repository nguyenthdat/burp-mcp (3 stars, last pushed 1mo ago), licensed MIT. It adds 168 tokens to every session and 3,830 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
opik-test
Turn a failing Opik trace (or a described failure) into a repeatable regression check — a test-suite item with the trace's input and one or two binary assertions — so a fix can be verified by the compare skill. Works over the SDK; uses the MCP write tool when connected. Returns the suite, the item, and the assertion.…
cortex-explore-memory
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you…
qmclaw-workbench
A local simulator for superconducting quantum-bit experiments, including measurements used to study and tune a qubit. It produces bounded synthetic results without connecting to laboratory hardware or quantum cloud services.
quantum-fermi-hubbard-vqe
A variational quantum simulation of the open-boundary Fermi–Hubbard chain, a model of particles hopping between sites and interacting when they occupy the same system. It maps the model to qubits with the Jordan–Wigner transformation and searches for a low-energy state.
quantum-grover
A Qiskit implementation of Grover's algorithm, a quantum search method that increases the chance of finding a marked item. It can explain the method, build an explicit quantum circuit, or run it with chosen inputs.