weavatrix 1.14.2 → 1.15.0

package/README.md

@@ -10,10 +10,11 @@
 **Give your coding agent repository evidence before it starts guessing.**
 
 Weavatrix is the native MCP product for repository intelligence. It gives
-Codex, Claude Code, and other coding agents 60 read-only operations over one
+Codex, Claude Code, and other coding agents 64 read-only operations over one
 revision-bound evidence graph: impact, architecture, APIs, Git history,
 duplicates, dead code, search, semantic links, temporal memory, exported
-n8n workflows, and Dify YAML apps. Those parsers are domains on Weavatrix
+n8n workflows, Dify YAML apps, Agent packages, Mermaid flowcharts, and
+Web3 ABI/consumer impact. Those parsers are domains on Weavatrix
 Core, not new MCP products. See
 [n8n](https://weavatrix.com/n8n), [Dify](https://weavatrix.com/dify), and
 [parsers](https://weavatrix.com/parsers).
@@ -46,7 +47,7 @@ weavatrix mcp .
 ```toml
 [mcp_servers.weavatrix]
 command = "npx"
-args = ["-y", "weavatrix@1.14.2", "mcp", "."]
+args = ["-y", "weavatrix@1.15.0", "mcp", "."]
 ```
 
 Pass an absolute repository path when the Codex process cwd is not the project
@@ -55,7 +56,7 @@ you intend to analyze.
 ### Claude Code
 
 ```sh
-claude mcp add weavatrix -- npx -y weavatrix@1.14.2 mcp .
+claude mcp add weavatrix -- npx -y weavatrix@1.15.0 mcp .
 ```
 
 ### Cursor
@@ -68,7 +69,7 @@ the plugin for the same server name:
   "mcpServers": {
     "weavatrix": {
       "command": "npx",
-      "args": ["-y", "weavatrix@1.14.2", "mcp", "${workspaceFolder}"]
+      "args": ["-y", "weavatrix@1.15.0", "mcp", "${workspaceFolder}"]
     }
   }
 }
@@ -77,13 +78,14 @@ the plugin for the same server name:
 Profiles expose bounded views of the same engine:
 
 ```sh
-npx -y weavatrix@1.14.2 mcp . --profile=all
-npx -y weavatrix@1.14.2 mcp . --profile=code
-npx -y weavatrix@1.14.2 mcp . --profile=seo
-npx -y weavatrix@1.14.2 mcp . --profile=n8n
-npx -y weavatrix@1.14.2 mcp . --profile=dify
-npx -y weavatrix@1.14.2 mcp . --profile=agent
-npx -y weavatrix@1.14.2 mcp . --profile=diagram
+npx -y weavatrix@1.15.0 mcp . --profile=all
+npx -y weavatrix@1.15.0 mcp . --profile=code
+npx -y weavatrix@1.15.0 mcp . --profile=seo
+npx -y weavatrix@1.15.0 mcp . --profile=n8n
+npx -y weavatrix@1.15.0 mcp . --profile=dify
+npx -y weavatrix@1.15.0 mcp . --profile=agent
+npx -y weavatrix@1.15.0 mcp . --profile=diagram
+npx -y weavatrix@1.15.0 mcp . --profile=web3
 ```
 
 The package contains native binaries for Windows x64/arm64, macOS x64/arm64,
@@ -200,7 +202,7 @@ Three commits before `ec8bf30` this package was 1.9.2; the agent reads that
 follow-up to a diff without touching the worktree. Binary blobs fail closed
 instead of being decoded into garbage.
 
-## The 60 read-only operations
+## The 64 read-only operations
 
 | Workflow | Operations |
 | --- | --- |
@@ -216,6 +218,7 @@ instead of being decoded into garbage.
 | Dify apps | `dify_inventory`, `dify_trace`, `dify_context` |
 | Agent packages | `agent_inventory`, `agent_trace`, `agent_context`, `agent_change_impact` |
 | Mermaid diagrams | `diagram_inventory`, `diagram_trace`, `diagram_context` |
+| Web3 integration | `web3_inventory`, `web3_trace`, `web3_impact`, `web3_context` |
 
 Every operation is read-only with respect to the analyzed repository.
 Pagination and explicit limits bound large neighborhoods, histories, searches,
@@ -247,6 +250,7 @@ export in git → existing JSON/YAML parse → typed domain → inventory / trac
 | [Dify](https://weavatrix.com/dify) | `dify_inventory`, `dify_trace`, `dify_context` | Product 1.13.0 |
 | Agent packages | `agent_inventory`, `agent_trace`, `agent_context`, `agent_change_impact` | Product 1.14.0 |
 | Mermaid diagrams | `diagram_inventory`, `diagram_trace`, `diagram_context` | Product 1.14.0 |
+| Web3 integration | `web3_inventory`, `web3_trace`, `web3_impact`, `web3_context` | Product 1.15.0 |
 
 | Need | Use |
 | --- | --- |
@@ -266,12 +270,12 @@ coding agent
     |
     | MCP over stdio
     v
-weavatrix 1.14.2
+weavatrix 1.15.0
     profile catalog · refresh · watcher · MCP framing
     |
     v
-weavatrix-rust 2.14.3
-    typed graph · analysis · 60 product operations including n8n, Dify, agent packages, and Mermaid
+weavatrix-rust 2.15.1
+    typed graph · analysis · 64 product operations including n8n, Dify, agent packages, Mermaid, and Web3
 ```
 
 This npm product owns MCP transport and native distribution. The

package/package.json

@@ -1,8 +1,8 @@
 {
   "name": "weavatrix",
-  "version": "1.14.2",
-  "weavatrixEngineVersion": "2.14.3",
-  "description": "Native repository intelligence for coding agents: 60 read-only MCP operations backed by typed evidence graphs, impact, architecture, APIs, Git, search, semantics, memory, n8n workflows, Dify apps, agent packages, and Mermaid diagrams.",
+  "version": "1.15.0",
+  "weavatrixEngineVersion": "2.15.1",
+  "description": "Native repository intelligence for coding agents: 64 read-only MCP operations backed by typed evidence graphs, impact, architecture, APIs, Git, search, semantics, memory, n8n workflows, Dify apps, agent packages, Mermaid diagrams, and Web3 ABIs.",
   "author": "Sergii Ziborov <sergii.ziborov@gmail.com>",
   "license": "MIT",
   "homepage": "https://weavatrix.com",

package/server.json

@@ -2,19 +2,19 @@
   "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
   "name": "io.github.Weavatrix/weavatrix",
   "title": "Weavatrix",
-  "description": "Native Weavatrix MCP: 60 read-only tools for code, n8n, Dify, agent packages, and Mermaid.",
+  "description": "Native Weavatrix MCP: 64 read-only tools for code, n8n, Dify, agents, Mermaid, and Web3.",
   "repository": {
     "url": "https://github.com/Weavatrix/weavatrix",
     "source": "github"
   },
-  "version": "1.14.2",
+  "version": "1.15.0",
   "websiteUrl": "https://weavatrix.com",
   "packages": [
     {
       "registryType": "npm",
       "registryBaseUrl": "https://registry.npmjs.org",
       "identifier": "weavatrix",
-      "version": "1.14.2",
+      "version": "1.15.0",
       "runtimeHint": "npx",
       "transport": {
         "type": "stdio"

package/skill/SKILL.md

@@ -6,7 +6,8 @@ description: >-
   impact, API/event tracing, architecture checks, Git/coverage evidence,
   duplicates, dead-code review, semantic context, exported n8n
   workflows, exported Dify YAML, Agent Plugins/Skills/MCP
-  catalogs, or Mermaid flowcharts. Skip it for trivial
+  catalogs, Mermaid flowcharts, or Web3 ABI and client
+  bindings. Skip it for trivial
   single-file edits or when a known source file and native tests already answer
   the task.
 ---
@@ -33,8 +34,10 @@ contracts. Do not call it merely because the server is available.
    exported Dify YAML, and `agent_inventory` / `agent_trace` /
   `agent_context` / `agent_change_impact` for Agent Plugins, Skills, and
   supplied MCP catalogs, and `diagram_inventory` / `diagram_trace` /
-  `diagram_context` for Mermaid flowcharts. Those paths are static graph
-  evidence, not a live n8n, Dify, MCP, or Mermaid runtime.
+  `diagram_context` for Mermaid flowcharts, and `web3_inventory` /
+  `web3_trace` / `web3_impact` / `web3_context` for supplied ABI,
+  artifacts, and static viem/wagmi consumers. Those paths are static graph
+  evidence, not a live n8n, Dify, MCP, Mermaid, or blockchain runtime.
 5. Use repository-native tests or benchmarks for behavioral proof.
 
 Do not call `open_repo` "just in case". Cross-repository tools take explicit

package/skill/references/tool-routing.md

@@ -107,3 +107,14 @@ engine `weavatrix-rust` 2.14.3.
 - [`diagram_inventory`](tools/diagram_inventory.md) — List diagrams, native elements, and explicit sidecar bindings.
 - [`diagram_trace`](tools/diagram_trace.md) — Walk `declared_architecture` arrows only.
 - [`diagram_context`](tools/diagram_context.md) — Fragments and binding status; display names are not IDs.
+
+## Web3 integration
+
+Local ABI JSON, supplied solc/Foundry artifacts, and static viem/wagmi
+sources only. Not a compiler, RPC client, or wallet. Requires engine
+`weavatrix-rust` 2.15.1.
+
+- [`web3_inventory`](tools/web3_inventory.md) — List ABIs, artifacts, and static consumers.
+- [`web3_trace`](tools/web3_trace.md) — Walk proven ABI, artifact, and consumer bindings.
+- [`web3_impact`](tools/web3_impact.md) — Interface deltas and consumer-specific effects, including silent event misdecode.
+- [`web3_context`](tools/web3_context.md) — Bounded fragments plus explicit deployment gaps.

package/skill/references/tools/web3_context.md

@@ -0,0 +1,33 @@
+# `web3_context`
+
+Bounded Web3 context: changed ABI fragment, proven call or decoder sites,
+and explicit deployment gaps.
+
+## When to use
+
+Inspect one ABI member or consumer after inventory. The `task` argument
+changes selection: event work needs filters and decoders; output work
+needs result consumers. A live chain is never queried.
+
+## Inputs
+
+- `label` (string, required) — graph id or unique Web3 member / consumer label.
+- `task` (string, optional) — what the caller intends to change or inspect.
+- `max_related` (number, optional) — related row cap, 1–200, default 24.
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+
+## Minimal call
+
+```json
+{
+  "name": "web3_context",
+  "arguments": {
+    "label": "Deposit(address,uint256)",
+    "task": "change-event",
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/web3_impact.md

@@ -0,0 +1,35 @@
+# `web3_impact`
+
+Compare supplied ABI revisions and report consumer-specific interface
+deltas, including silent event misdecode risk.
+
+## When to use
+
+A contract ABI changed and a client still binds an older copy. An indexed
+mask change can decode without throwing. Deployment state stays
+`not_provided` unless a runtime observation was supplied.
+
+## Inputs
+
+- `path` (string, optional) — repository-relative path fragment used when baseline/candidate are omitted.
+- `baseline` (string, optional) — repository-relative consumer or previous ABI path.
+- `candidate` (string, optional) — repository-relative provider or new ABI path.
+- `provider` (string, optional) — alias for candidate.
+- `task` (string, optional) — selection hint such as `change-event`, `change-input`, or `change-output`.
+- `max_results` (number, optional) — change page size, 1–200, default 50.
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+
+## Minimal call
+
+```json
+{
+  "name": "web3_impact",
+  "arguments": {
+    "task": "change-event",
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/web3_inventory.md

@@ -0,0 +1,29 @@
+# `web3_inventory`
+
+List supplied contract ABIs, compiler artifacts, and static viem/wagmi
+consumers without touching a chain.
+
+## When to use
+
+Orient on ABI JSON, solc/Foundry artifacts, and client call sites already
+in the repository. ABI equality is not a deployment proof.
+
+## Inputs
+
+- `path` (string, optional) — repository-relative ABI, artifact, or consumer path fragment.
+- `max_results` (number, optional) — inventory page size, 1–500, default 200.
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+
+## Minimal call
+
+```json
+{
+  "name": "web3_inventory",
+  "arguments": {
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.

package/skill/references/tools/web3_trace.md

@@ -0,0 +1,32 @@
+# `web3_trace`
+
+Walk proven ABI, artifact, and consumer bindings for one Web3 member or
+call site.
+
+## When to use
+
+After `web3_inventory`, when a function or event name is not enough: follow
+the exact occurrence to its ABI member and static client binding.
+
+## Inputs
+
+- `label` (string, required) — graph id or unique Web3 member / consumer label.
+- `depth` (number, optional) — walk depth, 1–32, default 8.
+- `max_nodes` (number, optional) — page size, 1–200, default 64.
+- `cursor` (string, optional) — opaque page token from a previous page.
+- `output_format` ("text" | "json" | "structured", default "json") — text returns the concise text block only; json returns structured output and mirrors it into text for clients that read only content; structured drops that mirror, which is the larger copy, and is safe only where the client reads structuredContent.
+
+## Minimal call
+
+```json
+{
+  "name": "web3_trace",
+  "arguments": {
+    "label": "Deposit(address,uint256)",
+    "output_format": "text"
+  }
+}
+```
+
+Use `output_format:"text"` for compact agent interaction. The live MCP
+`tools/list` schema remains authoritative for this installed version.