This is an automated email from the ASF dual-hosted git repository. davsclaus pushed a commit to branch quick-fix/mcp-doc-tools in repository https://gitbox.apache.org/repos/asf/camel.git
commit 9628758c434f8cff2ab6c580ff6528fe166b6cf9 Author: Claus Ibsen <[email protected]> AuthorDate: Thu Sep 24 08:00:50 2026 +0200 chore: document the seven camel-jbang-mcp tools the page was missing The page listed 74 of the 81 tools the server exposes. Missing were camel_ai_pipeline_scaffold, camel_dependency_security_audit, camel_route_cost_estimate, camel_runtime_ai_trace, camel_runtime_heap_dump, camel_runtime_processor_detail and camel_security_scan. Each is described from its own tool description and placed next to its relatives: the three runtime ones beside route_structure, heap_histogram and trace, the two security ones in Security Analysis, the cost estimate in Route Understanding, and the pipeline scaffold in a new AI Pipelines section since it generates a route rather than analysing one. The five names in the page that the server does not expose as tools - camel_build_integration, camel_diagnose_route, camel_migrate_project, camel_optimize_route and camel_security_review - are prompts, and are already documented as such under "Prompts (structured workflows)". Co-Authored-By: Claude Opus 5 (1M context) <[email protected]> Claude-Session: https://claude.ai/code/session_01Bp3538HRBPMQkb5ta9xRaj --- .../modules/ROOT/pages/camel-jbang-mcp.adoc | 46 ++++++++++++++++++++++ 1 file changed, 46 insertions(+) diff --git a/docs/user-manual/modules/ROOT/pages/camel-jbang-mcp.adoc b/docs/user-manual/modules/ROOT/pages/camel-jbang-mcp.adoc index 7dfeda56011f..7afa912d338d 100644 --- a/docs/user-manual/modules/ROOT/pages/camel-jbang-mcp.adoc +++ b/docs/user-manual/modules/ROOT/pages/camel-jbang-mcp.adoc @@ -437,6 +437,12 @@ project `directory` as an argument, the runtime tools take the integration `name | `camel_route_context` | Given a Camel route (YAML, XML, or Java DSL), extracts all components and EIPs used, looks up their documentation from the catalog, and returns structured context. + +| `camel_route_cost_estimate` +| Estimates the API cost of a route from the components it uses, for the ones with pay-per-use pricing: Bedrock + (runtime and agent-runtime), Textract, S3, SQS, SNS, Kinesis, OpenAI, LangChain4j (chat and embeddings) and + Docling (free, self-hosted). Returns a per-execution estimate and a monthly projection at a given throughput. + The cost data is approximate, from published AWS pricing (2025-Q2). |=== === Test Scaffolding @@ -457,6 +463,18 @@ project `directory` as an argument, the runtime tools take the integration `name test dependencies. |=== +=== AI Pipelines + +[cols="1,3",options="header"] +|=== +| Tool | Description + +| `camel_ai_pipeline_scaffold` +| Generates a YAML DSL route for an AI document-processing pipeline, combining a document processor (Docling for + open-source or on-premise, Textract for AWS-managed) with Bedrock LLM services for summarization, extraction, + RAG or classification. Returns a runnable route and a matching `application.properties` template. +|=== + === Security Analysis [cols="1,3",options="header"] @@ -475,6 +493,19 @@ project `directory` as an argument, the runtime tools take the integration `name and severity. Each advisory includes the summary, affected and fixed versions, mitigation, and a best-effort verdict on whether the given Camel version is affected. Use it to answer questions such as "is my Camel 4.10.1 project affected by known CVEs?". + +| `camel_security_scan` +| Scans a route for security anti-patterns by static analysis: secrets exposed in URIs, insecure configuration + options (`trustAllCertificates`, `allowJavaSerializedObject` and the like), missing `Camel*` header filters on + consumers, unencrypted protocols and other violations of the Camel security model. Each finding carries a + severity, a line number and remediation guidance. Distinct from `camel_route_harden_context`, which gives + general security context and the CVE advisories. + +| `camel_dependency_security_audit` +| Audits a project's dependencies for known vulnerabilities: cross-references the `pom.xml` with the Camel + security advisory database for the CVEs affecting each artifact at the project's Camel version, and reports + severity, affected and fixed version ranges, and whether the vulnerable component is actually used (reachable) + or only a transitive dependency. The POM content is sanitized to mask sensitive data. |=== ==== Security advisory data @@ -653,6 +684,11 @@ process is running). | `camel_runtime_route_structure` | Show the route structure as a tree of processors. +| `camel_runtime_processor_detail` +| Show the configured options of every processor in a route: each processor's type, id, and configured options + (attributes and expressions). With `includeDocs=true` each EIP option and component endpoint option is enriched + with its documentation from the Camel catalog. + | `camel_runtime_route_control` | Control a route: start, stop, suspend, or resume it by route ID. @@ -689,6 +725,10 @@ process is running). | Get a class-level heap histogram showing instance counts and byte usage per class. Useful for diagnosing memory leaks and understanding which classes dominate heap usage. +| `camel_runtime_heap_dump` +| Write a heap dump (`.hprof`) from a running integration for deep memory analysis with tools such as Eclipse MAT, + VisualVM or jhat. The dump is written to the process working directory. + | `camel_runtime_memory_leak` | Diagnose memory leaks in a running Camel integration using Java Flight Recorder (JFR). Use command 'start' to begin recording, 'stop' to get results, 'status' to check state, @@ -773,6 +813,12 @@ process is running). | `camel_runtime_trace` | Enable, disable, or dump message tracing for the running Camel application. +| `camel_runtime_ai_trace` +| Trace the AI-specific exchange flow of a running application: token usage, model ids, guardrail outcomes, + completion reasons, streaming chunk counts and per-component latency for the AI components (Bedrock, + LangChain4j, Docling, Textract, OpenAI, KServe, DJL, TensorFlow Serving, HuggingFace). It combines the message + history with the processor statistics, filtered to the AI steps. + | `camel_runtime_browse` | Browse messages in a Camel endpoint (e.g., messages queued in a SEDA endpoint).
