comol/ai_rules_1c/mcp-1c-tools

Claude Code and agent skill by comol/ai_rules_1c

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Router for non-memory 1C MCP operations: select the server, operation skill with exact arguments, and fallback. Load before choosing a 1C tool; memory-only work enters through project-memory.md.

Install

npx vskill@latest install comol/ai_rules_1c/mcp-1c-tools

SKILL.md

MCP tools for 1C — router

Apply content/rules/mcp-policy.md → Tool availability before routing: .dev.env TOOL_* policy plus callable tools and verified scope. Config entries alone prove nothing. The same policy owns obligations, budgets and typed-error recovery. Search: content/rules/mcp-first-search.md; task sequences: content/rules/tooling-playbooks.md.

Project scope is part of the call. For extensions or a multi-project graph, first match the current source roots to a returned base project_id through list_graph_projects (content/rules/multi-contour-search.md). Supply it explicitly on every graph project-data call that exposes it, including paging and evidence. Resolve extension-layer coverage separately. Use each other server's actual selector (configurationId or another field only if exposed); its identifiers are not interchangeable with graph IDs. If a tool has no explicit selector, require a verified fixed/session/entity scope or use a suitable scoped tool/fallback. Never invent unsupported parameters or accept a default/foreign project as the current one. Reuse a valid mapping until the workspace/server context changes.

Need → operation skill

Load the skill for the operation, not this whole catalogue. Each skill lists the exact argument names of its tools and example calls; no schema fetch is needed for a tool it names.

NeedSkillServers
Locate or read BSL code, module layout, members of a contextcontent/skills/1c-code-search/SKILL.mdgraph, code
Facts about a metadata object: passport, attributes, tabular-part columns, objects by category or descriptioncontent/skills/1c-meta-info/SKILL.mdgraph, code
Usages, call chains, downstream impact, register writers, extension layerscontent/skills/1c-impact/SKILL.mdgraph, code
Read forms, form artifacts, XSD / format specs before a form changecontent/skills/1c-form-inspect/SKILL.mdcode, graph, docs
Validate changed BSL and metadata XML (Gates 1–3, 5)content/skills/1c-validate/SKILL.mdsyntax, checker, code
Platform reference, capability check, БСП API, routed standards, ITS, configuration docscontent/skills/1c-platform-help/SKILL.mddocs, ssl, checker, code
Templates as the basecontent/skills/1c-templates-memory/SKILL.mdtemplates
Memory recall / save (independent entry point)content/rules/project-memory.mdcognee, openviking, templates
Run a query or fragment in the live infobase, last event-log errorcontent/skills/1c-live-ib/SKILL.mddata
Check behaviour in the 1C interface (thin client): forms, fields, tables, commands, messagescontent/skills/1c-qa-testing/SKILL.md + content/rules/qa-testclient.mdqa
Create / edit / remove metadata, forms, roles, DCS, MXL, infobasescontent/skills/1c-metadata-manage/SKILL.mdscripts, not MCP
Live 1C:EDT workspace (USE_EDT=true only)docs/edt-mcp.md, content/rules/edt-workflow.mdedt

Server catalog

The operation table above is sufficient for ordinary routing. Read server-catalog.md only to identify an unfamiliar server/alias, find a server-specific reference, or select an optional pre-alpha integration. Do not load the whole catalog before a known operation.

Fallback chain

Project source (code, metadata, usages, forms, file locations): within verified contour coverage, graph → mapped code-metadata → scoped native Grep / Glob / Read after a bounded miss, with a one-line fallback note. Code chooses its file-scan fallback internally; current tools have no grep input. Skip uncovered lanes; no eligible exposed index means native search in that contour immediately. Owner: content/rules/mcp-first-search.md; multiple roots, catalog/scope selectors and acceptance: content/rules/multi-contour-search.md.

External knowledge has no interchangeable fallback chain. Select only the relevant eligible provider. Missing templates: disclose no template check; memory: project-memory.md; routed standards: help-corpus-retrieval.md; validators/live IB: verification-gates.md. An unavailable source never proves API absence or a passed check; block dependent design when authoritative facts are missing.

Open docs/<server>.md once per server per session and only for a mode or response shape the operation skill does not cover; the environment descriptor wins over any document here.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/comol/ai_rules_1c/mcp-1c-tools/badge)](https://verified-skill.com/skills/comol/ai_rules_1c/mcp-1c-tools)

Something wrong with this skill or its page? Tell us.