MCP server for Flikt.AI — browse plan-review results, ask questions, export RFIs, and start reviews from Claude
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"flikt-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# flikt-mcp MCP server that connects Claude (Claude Code, Claude Desktop, or any MCP client) to your [Flikt.AI](https://flikt.ai) account: browse plan-review results, dig into coordination conflicts, ask questions, export RFI packages, and — if you allow it — kick off reviews of uploaded plan sets. ## Setup 1. **Mint a token** in the Flikt portal: **Settings → API access → Create token**. Default tokens are read-only. Check *"Allow this token to start reviews"* (and set a monthly page limit) only if you want Claude to be able to start reviews against your subscription's page allowance — a token can never charge your card; runs that aren't fully covered by your plan are refused. 2. Copy the token at creation — it is shown exactly once. 3. **Add the server** (Claude Code): ```bash claude mcp add flikt \ --env FLIKT_API_TOKEN=flk_your_token_here \ -- python -m flikt_mcp ``` or in any MCP client config: ```json { "mcpServers": { "flikt": { "command": "python", "args": ["-m", "flikt_mcp"], "env": { "FLIKT_API_TOKEN": "flk_your_token_here" } } } } ``` Install first with `pip install .` (from this directory), or run via `uvx --from <path-to-flikt-mcp> flikt-mcp`. `FLIKT_API_BASE` overrides the API host (default `https://api.flikt.ai`). ## Tools | Tool | Token permission | What it does | |---|---|---| | `list_projects` | read | Projects with open-conflict severity rollups + review status | | `get_project` | read | One project's summary + latest submission id | | `list_conflicts` | read | Open conflicts (filter by severity / discipline / ball-in-court) | | `ask_project` | read | Q&A over results: cost exposure, counts, top risks, schedule impact | | `check_review_status` | read | Poll a running review (`uploaded` → `processing` → `complete`) | | `save_rfis_pdf` | read | Download the ready-to-send RFI package to a local file | | `run_review` | **start reviews**…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.