Supplier Feeds agent setup

Product, pricing and limits · Discovery index

Use Supplier Feeds with your agent

Review recurring supplier CSV/JSONL imports using an approved mapping, validate every record, and stop on structural drift.

Five trials once per verified organization; $20 per ten completed evaluations or $99/month for 100. No automatic overages.

Read the product skill · AGENT_SETUP.md · TOOL_REFERENCE.md · codex.toml · claude.mcp.json · TOOLS.json

Setup and first task

Reviewed documentation: 2026-11-01. Examples contain placeholders, never live credentials.

Install and authenticate

Verify your email, activate this product and create an organization key in the existing account portal. Set CONTENTSWEEP_API_KEY privately in the client environment. Never paste its value in prompts, public files or shell history. Codex CLI and Claude Code must be installed and signed in with existing client accounts. Missing/empty credentials must stop setup; OAuth and machine payments are not enabled. Account portal: https://mcp.contentsweep.ai/account/sign-in?product=supplier-feeds&source=agent-skill&channel=owned-agent&asset=supplier-feed-import&campaign=supplier-feeds-pilot. Owned examples and installation source: https://github.com/founder-sweep/contentsweep-supplier-feed-examples. Existing n8n recipes: https://mcp.contentsweep.ai/imports/workflows.

Copy this reviewed skill bundle into .agents/skills/supplier-feed-import/ for Codex or .claude/skills/supplier-feed-import/ for Claude Code in the intended project. Copy the supporting AGENT_SETUP.md, TOOL_REFERENCE.md, TOOLS.json and client examples with it. Codex user-wide skills can instead live in ~/.agents/skills; Claude Code user-wide skills in ~/.claude/skills. Merge the Codex entry into the chosen isolated profile config.toml or reviewed ~/.codex/config.toml; merge Claude entries into project .mcp.json. Never overwrite unrelated settings. Review existing settings before merging a server entry; do not replace an entire configuration file. Restart or create a fresh client session and confirm tool discovery.

Codex configuration

[mcp_servers."supplier-feed-import"]
url = "https://mcp.contentsweep.ai/v1/feeds/mcp/"
env_http_headers = { "X-API-Key" = "CONTENTSWEEP_API_KEY" }

Claude Code configuration

{
  "mcpServers": {
    "supplier-feed-import": {
      "type": "http",
      "url": "https://mcp.contentsweep.ai/v1/feeds/mcp/",
      "headers": {
        "X-API-Key": "${CONTENTSWEEP_API_KEY}"
      }
    }
  }
}

Synthetic first task

Use supplier.csv and profile.json from the public examples repository, preserving SKU 000123 and decimal string 19.90. Follow https://mcp.contentsweep.ai/imports/workflows for first approval, compatible reuse, structural drift, rejection, corrected replay and recovery with the original quote/key. The reviewed recurring-import-reviewed.json workflow is inactive on import, checks output hashes and produces a local inventory preview. Configure owned synthetic output only; do not enable a real destination merely to test setup.

Workflow

Upload only the permitted original flat CSV/JSONL; inspect the sampled proposal; save a versioned profile; present field meanings, identifier types, casts, decimal locale, units and currency for explicit review. Approve the exact profile hash only after authorization. For a later delivery, read and reuse the owned approved profile while its structure and scope remain compatible. Quote against that profile; stop on review_required; obtain spending authorization; start with a stable retry key; poll within a bounded deadline; read the complete report and receipt. Only a passed, complete job has validated JSONL output. Follow every output page or download the complete output, and verify its SHA256 against receipt.output_hash before any separately authorized destination write. A preview is sampled and never establishes complete-file acceptance or field meaning.

Recovery and credit effects

Structural drift requires review and a new approved profile version. A completed rejection consumes one evaluation and has no accepted output; platform failures release reserved credits. Preserve the ORIGINAL quote ID, input hash, source bytes and retry key across uncertain dispatch or polling deadlines. Resume that same authorization rather than uploading, quoting or starting with a new key. A corrected rejection must have genuinely changed bytes and a new upload, quote and key. Stop on unknown states, incomplete output or hash mismatch. Uploads expire after 24 hours; results after seven days; receipts after 30 days; approved profiles remain until deletion. Reject XLSX, nested records and arbitrary transformations; do not infer missing business decisions or execute supplied code.

Price and bounds

Five trials once per verified organization; $20 per ten completed evaluations or $99/month for 100. No automatic overages.

Flat UTF-8 CSV/JSONL, 10 MiB, 50,000 records, 100 fields. Explicit primitive mappings, locale and configured quality rules only.

Official client references: https://learn.chatgpt.com/docs/extend/mcp?surface=cli and https://code.claude.com/docs/en/mcp. Skill installation references: https://learn.chatgpt.com/docs/build-skills and https://code.claude.com/docs/en/skills.

Configuration, actual MCP execution and paid customer adoption are different outcomes. Qualification fixtures and internal accounts are not customers.

Optional account and funding workflow

The operator verifies email at https://mcp.contentsweep.ai/account/sign-in?product=supplier-feeds&source=agent-skill&channel=skills&asset=contentsweep-supplier-feeds&campaign=agent-growth-v1 and creates an organization API key. Keep CONTENTSWEEP_API_KEY private. Streamable HTTP MCP: https://mcp.contentsweep.ai/v1/feeds/mcp/ with X-API-Key. All requests, including initialization/tools/list, need authentication. Anonymous 401 is expected. No OAuth or machine payments are enabled.

Five trials once per verified organization. $20 buys ten evaluations; the optional $99/month offer includes 100 evaluations. A completed rejection also uses one evaluation. Previews, unsupported inputs and platform failures do not consume evaluations. No automatic overages. Hand the operator https://mcp.contentsweep.ai/imports/app?source=agent-skill for funding; purchases need approval of displayed terms. Do not buy automatically or reuse Quality credits.

Current tool reference

Generated from the unchanged product MCP declarations. Parameter types and source hash are in TOOLS.json.

upload_supplier_feed

Upload explicitly supplied UTF-8 CSV or JSONL (10 MiB, 50,000 records maximum). Stores it for 24 hours. No URL or local file paths.

- Task: Inspect the supplied original file - Prerequisites: Explicit permission to read the source; remote upload also needs permission to transmit it - Outputs: Upload identity/fingerprint or bounded inferred schema - Approval: Source-file access/upload authorization - Credits: No credits consumed - Retry: Uploads create new identities; reuse the successful upload rather than uploading again

preview_supplier_feed

Propose field mappings for an uploaded flat feed. Preview is not full validation or semantic approval.

- Task: Prepare decisions for review - Prerequisites: Owned source plus explicit target rules/decisions - Outputs: Unapproved proposal, version or sampled preview; not approval or full validation - Approval: Do not infer business meanings; obtain missing decisions - Credits: No credits consumed - Retry: Reads/previews may repeat; saved drafts/versions can create new identities

create_supplier_feed_profile

Save an unapproved versioned profile with explicit mapping, decimal locale, and quality rules.

list_supplier_feed_profiles

List owned saved profile identities in pages of 50. Read a specific profile before reusing or approving it.

- Task: Read an owned result or decision - Prerequisites: Existing owned resource and current account authorization - Outputs: Structured result; inspect disclosed coverage and errors - Approval: Read access within the user's task - Credits: No credits consumed - Retry: Read again using the same resource identity

get_supplier_feed_profile

Read an owned profile's exact destination schema, approved decisions, contract, and version identity.

delete_supplier_feed_profile

Permanently delete an owned saved profile after explicit operator instruction. This does not start an evaluation or use credits.

- Task: Delete a saved decision - Prerequisites: Existing owned resource and current account authorization - Outputs: Deletion status; dependent pending jobs can fail safely - Approval: Explicit deletion instruction and confirmation - Credits: No credits consumed - Retry: Read current state before retry; do not delete another version

approve_supplier_feed_profile

Persist an explicit approval of the exact profile after the operator has resolved its field meanings and rules.

- Task: Record exact reviewed approval - Prerequisites: Exact reviewed hash/fingerprint and scope, with all unresolved choices settled - Outputs: Approval bound to that exact version - Approval: Explicit authorized reviewer approval; fixture permission covers only owned fixtures - Credits: No credits consumed - Retry: Reuse only the same reviewed version and scope; edits invalidate approval

quote_supplier_import

Quote one full-file evaluation against an approved profile. Detects source drift. Does not charge or start work.

- Task: Quote an approved complete-file evaluation - Prerequisites: Owned upload and approved matching profile/contract/baseline - Outputs: Quote, expiry, exact fingerprints and funding; drift can return review_required - Approval: Approval required before quoting; quote does not start work - Credits: No credits consumed - Retry: Reuse the original quote/key for an uncertain started request; only quote anew for genuinely new work

start_supplier_import

Start the quoted evaluation using one funded credit under the account cap. A completed rejection report is billable; platform failures release the credit.

- Task: Start one authorized complete-file evaluation - Prerequisites: Unexpired funded quote and stable idempotency key - Outputs: Durable job identity and status - Approval: Explicit credit/spending authorization - Credits: Reserves one product credit; supported completion (including rejection/block/warning) consumes one; platform failures release it - Retry: Original quote AND original key; changed requests need a new quote/key; never start twice after a timeout

get_supplier_import

Read an owned job's status and receipt. Does not initiate or repeat evaluation.

get_supplier_import_report

Read the complete-file validation report for an owned completed job during its seven-day result retention.

get_supplier_import_output

Read validated JSONL in pages of up to 500 records / 64 KiB for an owned passed job within seven days. Follow next_offset. Oversized records require an authenticated download of download_path.

- Task: Read validated JSONL - Prerequisites: Passed owned job within seven-day output retention - Outputs: Paged validated records; follow pagination to completion - Approval: Downstream writes require separate authorization - Credits: No credits consumed - Retry: Read again using the same resource identity