# @inflectiv-ai/inflectiv-mcp Search, build and manage Inflectiv datasets and AI agents, plus ChainAware on-chain intelligence. - **Type:** MCP server - **Trust:** 60/100 (B), scored on the package rubric - **Verification:** community-indexed — nobody has claimed this listing - **Version:** 1.2.0 - **Author:** io.github.inflectiv - **License:** Unknown - **npm:** @inflectiv-ai/inflectiv-mcp - **Source:** https://github.com/inflectiv/inflectiv-mcp-server - **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport) ## Trust 60/100 (B), scored on the package rubric - Publisher verified: no - Install scripts: nothing suspicious found - Prompt-injection scan: not run - Obfuscation scan: not run - Evidence age: 33 days ## Security scan - **Status:** clean - **Scanned:** 2026-09-01T18:27:30.956Z - **Version scanned:** 1.2.0 - **CVEs:** none found by OSV at scan time ## Tools 33 declared. Statically extracted from the shipped source — a floor on the surface, not a census. - `inflectiv_list_agents` — List all agents owned by you that have the API key's dataset attached. Free. - `inflectiv_create_agent` — Create a new AI agent. Per-dataset key auto-attaches to the key's dataset. Global key may pass dataset_ids (each must be accessible). Costs 5 credits. - `inflectiv_get_agent` — Get details of a specific agent. Free. - `inflectiv_update_agent_config` — Update an agent's configuration (personality, instructions, model, temperature, etc.). Costs 2 credits. - `inflectiv_chat_with_agent` — Send a message to an agent and get a RAG-enabled response. Costs 1 credit. Provide conversation_history as an array of {role, content} objects for multi-turn ch - `inflectiv_list_agent_datasets` — List all datasets attached to an agent. Free. - `inflectiv_attach_dataset` — Attach a dataset to an agent. Free. Mode can be "read_only" or "self_learning". - `inflectiv_update_dataset_mode` — Update the mode of a dataset attached to an agent. Mode: "read_only" or "self_learning". Free. - `inflectiv_list_datasets` — List datasets accessible via this API key. Per-dataset key returns the bound dataset. Global key returns every dataset the user owns + active marketplace acquis - `inflectiv_create_dataset` — Create a new dataset. Requires a global API key (inf_global_*). Cost: per credit_costs table. - `inflectiv_clone_dataset` — Clone an accessible dataset into the user's account. Requires a global API key. - `inflectiv_update_dataset` — Update dataset name, description, and/or instructions. Only the dataset owner can update. Free. - `inflectiv_reindex_dataset` — Reindex dataset vectors. Useful after bulk changes. Costs 2 credits. - `inflectiv_search_dataset` — Semantic search across a dataset's knowledge base. Costs 1 credit. - `inflectiv_batch_search` — Run multiple semantic searches against a single dataset. Costs 1 credit per query. - `inflectiv_cross_query` — Run one query against multiple accessible datasets at once. Requires a global API key + advanced tier. Costs 1 credit per dataset queried. - `inflectiv_write_intelligence` — Write a single intelligence entry to a dataset. Costs 1 credit (0 if duplicate). Content is embedded and becomes searchable. - `inflectiv_batch_write_intelligence` — Write multiple intelligence entries to a dataset. Costs 1 credit per new entry (duplicates are free). Max 50 entries. - `inflectiv_list_intelligence` — List intelligence entries in a dataset. Free. Filter by agent_id, status, with pagination. - `inflectiv_list_files` — List files (knowledge sources) in a dataset. Free. - `inflectiv_get_file` — Get details of a specific file (knowledge source). Free. - `inflectiv_upload_file` - `inflectiv_reprocess_file` — Reprocess a previously uploaded file. Useful after processing failures. Costs 5 credits. - `inflectiv_list_knowledge_sources` — List ALL knowledge sources in a dataset (files, URLs, manual text, AI-generated, etc.). Free. - `inflectiv_register_webhook` - `inflectiv_list_webhooks` — List all registered webhooks. Free. - `inflectiv_test_webhook` — Send a test event to a registered webhook to verify it's receiving payloads. Free. - `inflectiv_chainaware_fraud` — ChainAware predictive fraud / AML risk analysis for a wallet. Spends paid credits; repeat lookups within the same UTC day are cached for free and unprovisioned - `inflectiv_chainaware_rug_pull` — ChainAware predictive rug-pull risk analysis for a wallet. Spends paid credits; same-day repeats are cached for free and unprovisioned lookups are not charged. - `inflectiv_chainaware_credit_score` — ChainAware on-chain credit score for a wallet. Spends paid credits; same-day repeats are cached for free and unprovisioned lookups are not charged. Requires the - `inflectiv_chainaware_behaviour` — ChainAware predictive behaviour profile / wallet segmentation for a wallet. Spends paid credits; same-day repeats are cached for free and unprovisioned lookups - `inflectiv_chainaware_token_rank` — ChainAware ranked token list for a network (paged + sortable). Spends paid credits; same-day repeats with identical args are cached for free. Requires the chain - `inflectiv_chainaware_token_rank_single` — ChainAware ranking for a single token by contract address. Spends paid credits; same-day repeats are cached for free. Requires the chainaware_api feature. ## Install **Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for. **Cautions** (coverage gaps and advisories — never blocking) - No publisher has proved control of this listing; it is indexed, not vouched for. **Config** (claude-code): ```json "{\n \"mcpServers\": {\n \"inflectiv\": {\n \"command\": \"npx\",\n \"args\": [\n \"-y\",\n \"@inflectiv-ai/inflectiv-mcp\"\n ]\n }\n }\n}" ``` ## Blast radius Moderate to extensive — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: mutates data; runs on your machine. - Floor 32, ceiling 56 (tier: unknown) - `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low. - This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score. ## Machine-readable views of this entry - Signed JSON: https://forgeregistry.com/api/v1/packages/%40inflectiv-ai%2Finflectiv-mcp - Install plan: https://forgeregistry.com/api/v1/packages/%40inflectiv-ai%2Finflectiv-mcp/install-plan - Alternatives: https://forgeregistry.com/api/v1/alternatives/%40inflectiv-ai%2Finflectiv-mcp - HTML page: https://forgeregistry.com/registry/%40inflectiv-ai%2Finflectiv-mcp - MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan` ## About this document Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.