{"serverId":"mcp-registry/in.enhanciar/enhanciar","tools":[{"name":"get_graph","fixed":{"name":"get_graph","description":"Return the community/knowledge graph manifest for visualisation.\n\nUseful when the calling agent wants the high-level structure of the\nkey's workspace (clusters, hub nodes, cross-references) rather than\nthe contents of any one page. Returns ``{nodes, edges, communities,\nstats}`` — exact shape mirrors the ``/api/wiki/graph`` REST endpoint.\n","inputSchema":{"type":"object","title":"get_graphArguments","properties":{}},"annotations":{"readOnlyHint":true}},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":128,"tokensAfter":128},{"name":"get_page","fixed":{"name":"get_page","description":"Fetch a single wiki page from the key's workspace.\n\nArgs:\n    category: One of ``entities | concepts | people | decisions |\n        sources | flows | infrastructure | tickets``.\n    name: Page slug (without ``.md`` extension), as returned by\n        ``list_pages`` / ``search_wiki``.\n\nReturns ``{category, name, content}`` — ``content`` is the full\nmarkdown body including YAML frontmatter. Returns ``{error: \"...\"}``\nif the page doesn't exist.\n","inputSchema":{"type":"object","title":"get_pageArguments","properties":{"name":{"title":"Name","default":"","type":"string"},"page":{"title":"Page","default":"","type":"string"},"path":{"title":"Path","default":"","type":"string"},"slug":{"title":"Slug","default":"","type":"string"},"title":{"title":"Title","default":"","type":"string"},"category":{"title":"Category","default":"","type":"string"}}},"annotations":{"readOnlyHint":true}},"changes":[{"kind":"schema","detail":"Added \"type\":\"string\" to untyped parameters: name, page, path, slug, title, category. Change to number/boolean/array where that's what you accept.","verify":true},{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":223,"tokensAfter":250},{"name":"get_process_map","fixed":{"name":"get_process_map","description":"Return the \"living map of how the company works\" for the key's workspace.\n\nA graph of process nodes (compiled skills), the external systems\nthey touch (GitHub, Slack, Jira, …), the wiki docs they were\nderived from, and team groups — with derived_from / uses /\nreferences edges. Use this when the agent wants the high-level\noperational structure rather than one skill's steps.\n","inputSchema":{"type":"object","title":"get_process_mapArguments","properties":{}},"annotations":{"readOnlyHint":true}},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":142,"tokensAfter":142},{"name":"get_skill","fixed":{"name":"get_skill","description":"Fetch one compiled skill by name (slug from ``list_skills``).\n\nReturns ``{name, markdown, meta}`` — ``markdown`` is the full\nagent-executable SKILL.md content (frontmatter + steps), ``meta``\nis the parsed frontmatter. Includes an ``error`` key when the\nskill doesn't exist (with the available names).\n","inputSchema":{"type":"object","title":"get_skillArguments","required":["name"],"properties":{"name":{"type":"string","title":"Name"}}},"annotations":{"readOnlyHint":true}},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":134,"tokensAfter":134},{"name":"list_pages","fixed":{"name":"list_pages","description":"List every wiki page the caller can see in the key's workspace.\n\nReturns a list of ``{category, name, title}`` records — feed each\none to ``get_page`` to fetch the full markdown body. Use this first\nwhen you want a directory view; for a specific question prefer\n``query`` which handles retrieval for you.\n","inputSchema":{"type":"object","title":"list_pagesArguments","properties":{}},"annotations":{"readOnlyHint":true}},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":119,"tokensAfter":119},{"name":"list_proposed_actions","fixed":{"name":"list_proposed_actions","description":"List the key's workspace's proposed actions (the approval queue).\n\nRead-only. Optionally filter by ``status`` (proposed / approved /\nexecuting / done / failed / dismissed). Returns ``{id, action_type,\nstatus, source, title, source_doc_id, external_id}`` per proposal.\n\nNOTE: MCP can read and PROPOSE actions but deliberately cannot approve\nor execute them — a human approves every action in the app UI.\n","inputSchema":{"type":"object","title":"list_proposed_actionsArguments","properties":{"status":{"type":"string","title":"Status","default":""}}},"annotations":{"readOnlyHint":true}},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":169,"tokensAfter":169},{"name":"list_repos","fixed":{"name":"list_repos","description":"List the repos ingested into the key's workspace.\n\nReturns ``{full_name, branch, last_ingested_at}`` records. Use this when\nthe agent needs to know what context is available before asking a\nquestion.\n\nReads what ingest actually recorded for this namespace: ``repos.json``\n(the repo→clone map every other read path resolves through) plus the\nper-repo ``_state`` files that carry the branch and the last run's\ntimestamp.\n\nIt used to read a Firestore subcollection ``users/{uid}/repos``, which\nwas wrong","inputSchema":{"type":"object","title":"list_reposArguments","properties":{}},"annotations":{"readOnlyHint":true}},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":175,"tokensAfter":175},{"name":"list_skills","fixed":{"name":"list_skills","description":"List the compiled skills (recurring procedures) in the key's workspace.\n\nSkills are agent-executable SKILL.md pages mined from that workspace's\nwiki by the skills compiler. Returns ``{name, title, description,\nconfidence, last_compiled, sources}`` records — feed a ``name`` to\n``get_skill`` for the full markdown. Empty list = nothing compiled\nyet (the user can run a compile from Enhanciar's UI or API).\n","inputSchema":{"type":"object","title":"list_skillsArguments","properties":{}},"annotations":{"readOnlyHint":true}},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":148,"tokensAfter":148},{"name":"query","fixed":{"name":"query","description":"Ask Enhanciar a natural-language question grounded in the key's workspace.\n\nThis is the high-level tool — use it for any \"what does X do\",\n\"why did we choose Y\", \"where is Z handled\" question. It runs\nthe full retrieval + synthesis pipeline and returns the answer\nplus citations.\n\nArgs:\n    question: Natural-language question.\n    model: Optional model id override (``gemini-2.5-flash``,\n        ``gpt-4o``, ``claude-sonnet-4-5``, etc.). If omitted the\n        saved default is used — the workspace'","inputSchema":{"type":"object","title":"queryArguments","required":["question"],"properties":{"model":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Model","default":null},"question":{"type":"string","title":"Question"}}},"annotations":{"readOnlyHint":true}},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":217,"tokensAfter":217},{"name":"search_wiki","fixed":{"name":"search_wiki","description":"Substring search across the wiki pages in the key's workspace.\n\nCheap and deterministic — no embedding required. Returns up to\n``limit`` (default 20, max 50) ``{category, name, title, snippet}``\nhits. The ``snippet`` is a short window around the first match,\nsafe to surface in chat as a citation preview.\n\nFor semantic / natural-language questions prefer ``query``.\n","inputSchema":{"type":"object","title":"search_wikiArguments","required":["query"],"properties":{"limit":{"type":"integer","title":"Limit","default":20},"query":{"type":"string","title":"Query"}}},"annotations":{"readOnlyHint":true}},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":170,"tokensAfter":170}],"toolsChanged":10,"tokensSaved":0,"todo":[{"tool":"get_page","params":["name","page","path","slug","title","category"]},{"tool":"get_skill","params":["name"]},{"tool":"impact","params":["depth","target"]},{"tool":"list_proposed_actions","params":["status"]},{"tool":"propose_action","params":["title","evidence","action_type","description"]},{"tool":"query","params":["model","question"]},{"tool":"search_wiki","params":["limit","query"]}],"note":"Deterministic fixes. Changes marked verify need a human look before shipping (renames, inferred annotations, inferred types, removed text). Parameter descriptions in `todo` need to be written by someone who knows the API."}