"GitNexus - Git Repository Management Tool or Platform" matching MCP tools:

• acc_search_documents

  ACC MCP

  Full-text search the ACC Docs repository of a project for drawings, specs, submittals, and other files via the APS Data Management search endpoint. When to use: The user wants to find a document by keyword (filename, sheet number, or metadata match). E.g. 'find the latest A-201 sheet' or 'search for mechanical specs on Tower project'. When NOT to use: Do not use to upload a file (use acc_upload_file); do not use to fetch issues/RFIs. If you already have a document URN, fetch it directly with an agent that has Data Management folder/item access. APS scopes: data:read account:read. No write scope required. Rate limits: APS Data Management ~50 req/min per app per endpoint; pageable (limit 200 upstream). Avoid tight query loops. Errors: 401 (APS token expired — refresh); 403 (user lacks Docs view permission on the project); 404 (project_id not found — verify 'b.' prefix and hub membership); 422 (invalid filter syntax — simplify query text); 429 (rate limit — back off 60s); 5xx (ACC upstream — retry with jitter). Side effects: None. Read-only and idempotent.

  Connector

• me.validation_history

  AI Design Blueprint Doctrine

  Pro/Teams — return the authenticated user's architect.validate run history with the Blueprint Readiness Score (0-100), letter grade (A-F), and tier (draft, emerging, production_ready). Three lookup modes: (1) `run_id=<id>` returns a SINGLE run with the full persisted result_json — use this to RECOVER a result when your MCP client tool-call timed out before architect.validate returned. The run completes server-side and persists; the run_id is surfaced in the first progress notification of every architect.validate call so you have the recovery handle even when your client gives up early. (2) `repository=<name>` returns the full per-run trend for that repository plus a regression diff between the latest two runs. (3) No arguments returns one summary per repository the user has validated, sorted by most recent. Use modes (2) or (3) BEFORE calling architect.validate again on the same repository — they tell you which principles regressed since the last run, so you can focus the new review on what is actually changing. Auth: Bearer <token>. Pro or Teams plan required.

  Connector

• get_creator

  Influship Influencer Marketing MCP

  Fetch the full record for a single creator by ID or exact platform username. Use this when you already have either: - a canonical creator UUID returned by `search_creators`, `semantic_search_creators`, `autocomplete_creators`, or `find_lookalike_creators`; or - an exact platform+username pair such as platform "instagram" and username "niickjackson". Pass `include: ['profiles']` to also receive the creator's social profile summaries when using a creator UUID. For platform+username inputs, this tool resolves through the profile endpoint and returns the profile record plus the underlying creator record, so you already get the matched profile context. Examples: - User: "Get creator 123e4567-e89b-12d3-a456-426614174000" -> call with id. - User: "Get @niickjackson on Instagram" -> call with platform "instagram" and username "niickjackson", or use `get_profile` if profile metrics are the main need. - User: "Tell me about @niickjackson and include his profiles" -> use platform "instagram" and username "niickjackson"; then use `get_profile`/`get_posts` for platform-specific metrics and content if needed. Use `lookup_profiles` for batch exact profile lookups.

  Connector

• memory_rename

  emem — Earth memory protocol

  Move (rename) a memory file from `old_path` to `new_path`. Both paths must stay under `/memories/`; `new_path` must not already exist. The file_cid is preserved (no re-sign) so the prior receipt still binds the bytes. Mirrors the `rename` verb in Anthropic's context-management-2025-06-27 memory tool spec. When to use: Call when the LLM wants to rename or move a memory file. Failure modes: source missing, destination already exists, path escapes `/memories/`.

  Connector

• dispatch_social_listening_researcher_async

  Heista

  Dispatch to the SOCIAL LISTENING RESEARCHER — multi-platform community-signal interpretation. Use for: "what are practitioners saying about X across platforms / what jargon is emerging in field Y / what is the cross-platform discourse around brand/topic Z". Treats T3 community sources as primary data, distinguishes cross-platform patterns from single-platform noise. ≥3 platforms sampled per brief. Returns: Signal map (Signal / Platforms / Volume / Sentiment + recency) + Per-platform evidence trail + Cross-platform vs single-platform classification + Confidence flag + Sources. NOT for: single-source thematic work (use dispatch_qualitative_researcher) / numerical sentiment effect sizes (use dispatch_quantitative_researcher). ASYNC version: returns { job_id } immediately, the specialist runs durably on a Vercel Workflow (no 300s timeout). Use this version when the specialist is expected to take >90s. Call get_dispatch_result(job_id) periodically (respect wait_ms_hint in the response) until status === 'completed' or 'failed'. Idempotent: same brief + same org reuses the same job_id, so retries don't fan out duplicate runs.

  Connector

• list_creator_videos

  SocialGPT

  List a public/competitor creator's videos by platform + handle. Sort by 'recent' or 'top' (best-performing); optionally with analysis inline. Only returns creators already in the analysis library — for one you haven't ingested yet this returns reason="creator_not_in_library" with a next_step of analyze_creator(platform, username), not an error.

  Connector

• get_profile

  Influship Influencer Marketing MCP

  Fetch a single social profile by (platform, username). Always use this first when the user gives an exact handle on a specific platform (for example "@niickjackson on Instagram") and you need the full profile: bio, follower/engagement metrics, recent activity, growth, and the canonical creator ID. Pass exactly the username they typed without the @ sign — case-insensitive matching is handled server-side. Do not use `search_creators` for an exact platform+username lookup. Examples: - User: "Pull @niickjackson on Instagram" -> use this tool with platform "instagram" and username "niickjackson". - User: "Tell me about instagram.com/niickjackson" -> parse the platform and username, then use this tool. - User: "Is @niickjackson a fit for Pixel?" -> use this tool first, then call `get_posts` and/or `match_creators` if the task needs content or fit analysis. Returns the profile record plus the underlying creator record. If you already have a creator UUID, use `get_creator` instead. For batch lookups by handle, use `lookup_profiles`.

  Connector

• search_creators

  Influship

  Find a creator by name/handle, while preserving legacy semantic creator search. Use this as the default creator lookup tool when the user gives a creator-ish string but not a canonical creator UUID: a handle, partial handle, display name, creator name, or profile-ish text. This is cheap, fast, and backed by the creator lookup index. If the user gives an exact handle on a specific platform (for example "@niickjackson on Instagram"), prefer `get_profile` first because it returns the full platform profile. If you need to resolve a rough creator name or partial handle first, use this tool with `query_type: "creator_lookup"`. For backward compatibility, this tool still accepts the old semantic-search fields (`platforms`, follower/engagement filters, `creator_kinds`) and routes legacy calls to the semantic endpoint unless the query clearly contains a handle/profile URL. For new topical/niche discovery calls such as "fitness creators in NYC" or "vegan recipe creators with high engagement", prefer `semantic_search_creators` because its name is explicit and less likely to be confused with exact creator lookup. Examples: - User: "Find @cris" -> use this tool with query "cris" and query_type "creator_lookup". - User: "Who is that fitness coach called Jane?" -> use this tool with query "Jane" and query_type "creator_lookup". - User: "Pull @niickjackson on Instagram" -> use `get_profile` with platform "instagram" and username "niickjackson". - User: "Find news creators with 1M+ followers" -> use `semantic_search_creators`, not this tool. Returns either autocomplete-style creator lookup results or legacy semantic results, depending on routing. Use returned creator IDs with `get_creator`, `find_lookalike_creators`, or `match_creators`; use returned platform usernames with `get_profile` or `get_posts`.

  Connector

• adcritter_get_platform_overview

  AdCritter for Builders

  Start here. Returns the AdCritter platform overview - what AdCritter is, the entity hierarchy (organization > advertiser > campaign > ad), the happy path for getting ads running, and how to navigate the other MCP tools. Applications built from this guidance are REST API clients that call /v1/ endpoints, not MCP tool callers. Before writing code, call adcritter_get_api_reference(entity, action) for each entity and action you plan to use - tool descriptions and parameter names describe conceptual behavior only, and do not match actual API routes, field names, query parameters, or response shapes.

  Connector

• wait_for_task

  Agent Router

  Wait for a platform agent task to complete and return its result. Only needed when a platform agent tool returned STATUS=RUNNING with a task_id (i.e. the task was still running after the initial 50s inline wait). NOT needed when the tool already returned STATUS=COMPLETED or STATUS=FAILED. NOT needed for a2a_call_agent — that always returns directly. Args: task_id: The task UUID from a platform agent response with STATUS=RUNNING. max_wait_seconds: Max seconds to wait (default 45, max 300).

  Connector

• scan_skill

  SecurityScan

  Scan a GitHub repository or skill URL for security vulnerabilities. This tool performs static analysis and AI-powered detection to identify: - Hardcoded credentials and API keys - Remote code execution patterns - Data exfiltration attempts - Privilege escalation risks - OWASP LLM Top 10 vulnerabilities Requires a valid X-API-Key header. Cached results (24h) do not consume credits. Args: skill_url: GitHub repository URL (e.g., https://github.com/owner/repo) or raw file URL to scan Returns: ScanResult with security score (0-100), recommendation, and detected issues. Score >= 80 is SAFE, 50-79 is CAUTION, < 50 is DANGEROUS. Example: scan_skill("https://github.com/anthropics/anthropic-sdk-python")

  Connector

• code_get_file

  searchcode

  Get code from a remote public git repository — either a specific function/class by name, a line range, or a full file. PREFERRED WORKFLOW: When search results or findings have already identified a specific function, method, or class, use symbol_name to extract just that declaration. This avoids fetching entire files and keeps context focused. Only fetch full files when you need a broad understanding of a file you haven't seen before. For supported languages (Go, Python, TypeScript, JavaScript, Java, C, C++, C#, Kotlin, Swift, Rust) the response includes a symbols list of declarations with line ranges. This is not a first-call tool — use code_analyze or code_search first to identify targets, then extract precisely what you need.

  Connector

• restore_version

  WebSlop

  DESTRUCTIVE: Restore an app to a previous version using git reset --hard. This permanently overwrites all current files with the state from the specified commit — any changes made after that commit will be lost and CANNOT be recovered. You MUST confirm with the user before calling this tool. Use list_versions to show the user available versions first.

  Connector

• search_charts

  Helm MCP

  List or search charts in a Helm repository. Provide a repository_url, then optionally filter by keyword (e.g. keyword='postgres'). Note: OCI registries (oci://) do not support browsing — for OCI you must already know the chart name, then call get_versions or get_values directly with that name.

  Connector

• sti_get_platforms

  Stimulsoft Documentation MCP Server

  List every Stimulsoft product/platform that has indexed documentation available through this MCP server. Returns a JSON array of { id, name, description } objects covering the full Stimulsoft Reports & Dashboards product line (Reports.NET, Reports.WPF, Reports.AVALONIA, Reports.WEB for ASP.NET, Reports.BLAZOR, Reports.ANGULAR, Reports.REACT, Reports.JS, Reports.PHP, Reports.JAVA, Reports.PYTHON, Server API, etc.). CALL THIS FIRST when the user's question is ambiguous about which Stimulsoft platform they are using, or when you need to pick a valid `platform` value to pass into `sti_search`. The returned platform `id` values are the exact strings accepted by the `platform` parameter of `sti_search`. This tool is cheap (no OpenAI call, no vector search) — call it freely whenever you are unsure about platform naming.

  Connector

• lookup_profiles

  Influship Influencer Marketing MCP

  Batch-fetch up to 100 profiles by (platform, username) pairs. Use this when the user has a list of handles and you need profile data for all of them at once (e.g., "give me follower counts for these 30 accounts I'm considering" or "which of @a @b @c are real accounts?"). One round-trip beats 30 calls to `get_profile`. Use this for exact batch handle lookup, not semantic discovery. For one exact platform+username pair, use `get_profile`. For partial or fuzzy handle/name input, use `search_creators` or `autocomplete_creators`. Use `semantic_search_creators` only for topical/niche/audience discovery where false-positive semantic matches are acceptable. Examples: - User: "Compare @a, @b, and @c on Instagram" -> use this tool for the exact handle batch. - User: "Give me follower counts for these 30 accounts" -> use this tool. - User: "Find wellness creators in Austin" -> use `semantic_search_creators`, not this tool. The response splits results into `data` (profiles found) and `not_found` (the (platform, username) pairs that weren't recognized). Profiles are returned in no particular order — re-correlate via the platform/username fields if you need to preserve input order.

  Connector

• find_lookalike_creators

  Influship

  Find creators SIMILAR to one or more seed creators. Use this when the user already knows a creator they like and wants more like them (e.g., "find creators like @therock", "find more creators like these three I just booked"). Seeds are blended via creator-profile + visual-style + fact embeddings to surface similar accounts. Seeds are passed in `seed_creator_ids` (canonical UUIDs) and/or `seed_profiles` (platform + username; resolve handles via `autocomplete_creators` first if needed). Returns a ranked list of similar creators with scores. `limit` caps results (default 25, max 100). Use the flat follower, engagement-rate, and verified fields to constrain results. Use `semantic_search_creators` instead when you have a topic/niche but no seed. Use `match_creators` when you have specific candidates and want to score their fit against a brief. Examples: - User: "Find creators like @niickjackson on Instagram" -> use this tool with `seed_profiles: [{ platform: "instagram", username: "niickjackson" }]`. - User: "Find news creators with 1M+ followers" -> use `semantic_search_creators`, not this tool.

  Connector

• get_profile

  Influship

  Fetch a single social profile by (platform, username). Always use this first when the user gives an exact handle on a specific platform (for example "@niickjackson on Instagram") and you need the full profile: bio, follower/engagement metrics, recent activity, growth, and the canonical creator ID. Pass exactly the username they typed without the @ sign — case-insensitive matching is handled server-side. Do not use `search_creators` for an exact platform+username lookup. Examples: - User: "Pull @niickjackson on Instagram" -> use this tool with platform "instagram" and username "niickjackson". - User: "Tell me about instagram.com/niickjackson" -> parse the platform and username, then use this tool. - User: "Is @niickjackson a fit for Pixel?" -> use this tool first, then call `get_posts` and/or `match_creators` if the task needs content or fit analysis. Returns the profile record plus the underlying creator record. If you already have a creator UUID, use `get_creator` instead. For batch lookups by handle, use `lookup_profiles`.

  Connector

• export_dataset

  DC Hub — Data Center & Power Intelligence

  Use when a user wants to pull their saved DC Hub shortlist OUT of the platform for offline analysis, a spreadsheet, or ingestion into another tool (PRO). Example: "Export my saved sites as GeoJSON for QGIS." — export_dataset format=geojson. Params: format ("csv" default, or "geojson"). Returns: the full file contents as text — CSV rows or a GeoJSON FeatureCollection of your saved sites with DCPI score, target MW, market, coordinates, and notes. Do NOT use to list sites in-chat (use list_saved_sites) or to save a new one (use save_site); this is the bulk-download path.

  Connector

• export_dataset

  DC Hub — Data Center Intelligence MCP Server

  Use when a user wants to pull their saved DC Hub shortlist OUT of the platform for offline analysis, a spreadsheet, or ingestion into another tool (PRO). Example: "Export my saved sites as GeoJSON for QGIS." — export_dataset format=geojson. Params: format ("csv" default, or "geojson"). Returns: the full file contents as text — CSV rows or a GeoJSON FeatureCollection of your saved sites with DCPI score, target MW, market, coordinates, and notes. Do NOT use to list sites in-chat (use list_saved_sites) or to save a new one (use save_site); this is the bulk-download path.

  Connector