mcp-registry/io.github.toasternet/delegaize · registry v1.0.3 · server reports v1.96.0
claude mcp add --transport http glimind https://glimind.com/mcp?ref=install-server. Other clientsAs of 2026-11-22 16:58 UTC, the DelegAIze MCP server is up (it requires sign-in) with a Glimind reliability score of 90/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks.
AI agents for CRM, mail, calendar, ERP and accounting - you approve. EU-hosted, OAuth.
Point your MCP client at this streamable-http endpoint: https://delegaize.innov-ai-tive.de/api/sb/functions/v1/mcp-server
Loading this server's tool list costs an agent ~223,356 tokens before any work — more than 99% of MCP servers.
Split rarely-used tools into a separate server or a toolset the client can enable, or expose one "search tools" entry point. Many agents load every connected server's tools into every request. How to fix →
1 tool definition(s) exceed ~1,200 tokens each (largest: delegate_to_user, ~1,757).
Move long reference material out of descriptions (link a doc or expose a resource), drop repeated examples, and collapse large enums. Trimming these to ~600 tokens saves ~1,157 tokens every session. How to fix →
1022 tools on one server. Tool-selection accuracy drops as the menu grows, and some clients (e.g. Cursor) cap the number of active tools.
Group tools by task into smaller servers or toolsets, and merge near-duplicates behind one tool with a mode parameter. How to fix →
7 tool(s) have parameters with no type (no type/enum/anyOf/$ref).
Give every parameter a "type" (or "enum"/"anyOf"). Untyped parameters make models guess — strings for numbers, objects for arrays. How to fix →
1 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.
Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →
Negotiates MCP 2024-11-05. Structured output, tool output schemas and elicitation arrived in 2025-06-18.
Upgrade the MCP SDK and negotiate 2025-06-18 or newer. How to fix →
No tool declares an outputSchema.
Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably. How to fix →
Requires authentication (Bearer); tool definitions could not be read anonymously.
If discovery should be public, allow initialize + tools/list without credentials and gate only tools/call. Directories and routers can then list your tools.
In the last 30 days: 0 tool(s) removed and 7 schema change(s).
Add new tools or optional parameters instead of renaming or removing; deprecate first (say so in the description) and remove later. Agents cache tool contracts. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. All of them as JSON: /v1/readiness/mcp-registry%2Fio.github.toasternet%2Fdelegaize/fixes
{
"name": "create_sap_supplier_invoice",
"description": "Post an incoming supplier invoice with PO reference (MIRO equivalent). Runs the 3-way match first and books ONLY if every line matches; deviations come back as a question for a human instead of a posting (allow_deviation only after a human approved). Also refuses a second invoice with the same supplier_reference for the same supplier. WRITES — permission gate + write log; dry run unless the connection is live.",
"inputSchema": {
"type": "object",
"required": [
"invoicing_party",
"document_date",
"supplier_reference",
"gross_amount",
"lines"
],
"properties": {
"park": {
"description": "true = park the invoice in SAP instead of posting it; 'bei_abweichung' = park only when the 3-way match deviates (instead of asking back). A duplicate invoice number is always refused.",
"type": "string"
},
"lines": {
"type": "array",
"items": {
"type": "object",
"required": [
"purchase_order",
"purchase_order_item",
"quantity",
"amount"
],
"properties": {
"unit": {
"type": "string",
"description": "Unit of measure"
},
"amount": {
"type": "number",
"description": "net amount of the line in document currency"
},
"quantity": {
"type": "number",
"description": "invoiced quantity in PO unit"
},
"purchase_order": {
"type": "string",
"description": "SAP purchase order number the line refers to"
},
"purchase_order_item": {
"type": "string",
"description": "Item number within the purchase order"
}
}
},
"description": "Invoice lines with PO reference (PO, PO item, quantity, amount, unit)"
},
"dry_run": {
"type": "boolean",
"description": "true = build and log the request but send nothing. Writes are ALWAYS dry runs while the tenant's SAP connection has write_mode \"dry_run\" (the default)."
},
"currency": {
"type": "string",
"description": "Currency code (ISO 4217, e.g. EUR)"
},
"tax_code": {
"type": "string",
"description": "default from the connection"
},
"company_code": {
"type": "string",
"description": "SAP company code to post in"
},
"gross_amount": {
"type": "number",
"description": "Gross invoice amount in document currency"
},
"posting_date": {
"type": "string",
"description": "default: today"
},
"document_date": {
"type": "string",
"description": "invoice date YYYY-MM-DD"
},
"allow_deviation": {
"type": "boolean",
"description": "true = book despite 3-way-match deviations; only after human approval"
},
"invoicing_party": {
"type": "string",
"description": "SAP supplier number"
},
"supplier_reference": {
"type": "string",
"description": "the supplier's invoice number"
}
}
},
"annotations": {
"title": "Create SAP supplier invoice",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}{
"name": "send_draft_email",
"description": "Send a REVIEW COPY of an email to the rep for approval — NOT to the lead. Renders exactly as the real send (same from-address/signature/placeholders via the lead+campaign) but is delivered to the reviewer and clearly marked as a draft: the subject is prefixed '[DRAFT — review copy]' and a banner naming the real intended recipient is prepended to the body. Recipient defaults to the authenticated caller's own account email; pass to_address to send the review copy somewhere else. Required: lead_id,",
"inputSchema": {
"type": "object",
"required": [
"lead_id",
"subject",
"body"
],
"properties": {
"bcc": {
"description": "Blind-copy recipients for this review copy — array or comma-separated string. The campaign's archive BCC is deliberately not applied to review copies.",
"type": "string"
},
"body": {
"type": "string",
"description": "Body text"
},
"lead_id": {
"type": "string",
"description": "ID of the lead"
},
"subject": {
"type": "string",
"description": "Subject line"
},
"to_address": {
"type": "string",
"description": "Where to send the review copy (default: caller's own email)"
},
"campaign_id": {
"type": "string",
"description": "ID of the campaign"
},
"intended_to": {
"type": "string",
"description": "The lead's real email, shown in the draft banner"
}
}
},
"annotations": {
"title": "Send draft email",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}{
"name": "send_email",
"description": "Send an email to a lead, a person (contact_id) or an organisation (account_id) — or to any address. Required: subject, body, and lead_id, contact_id, account_id or to_address (to_address defaults to the record's e-mail). Sender: from_email picks one of the tenant's connected mailboxes (own SMTP server, Microsoft or Google); as_me=true sends with your name and sets Reply-To to your address so answers reach you; or set reply_to. If the tenant has switched off external providers (mail_only_own_serv",
"inputSchema": {
"type": "object",
"required": [
"subject",
"body"
],
"properties": {
"bcc": {
"description": "Extra blind-copy recipients for THIS send — array or comma-separated string. ADDS TO the campaign's bcc_emails, it does not replace them; set the campaign field for a copy that cannot be forgotten. Invalid addresses are dropped and logged, they never block the send.",
"type": "string"
},
"body": {
"type": "string",
"description": "Body text"
},
"as_me": {
"type": "boolean",
"description": "Your name as sender name, Reply-To your login address."
},
"lead_id": {
"type": "string",
"description": "ID of the lead"
},
"purpose": {
"type": "string",
"description": "The processing purpose of THIS mail (e.g. akquise, newsletter, bestandskunde, rechnung). A consent is always for ONE purpose: whoever agreed to the newsletter did not agree to cold outreach, so without a purpose the check can only look at the record's state and at withdrawals. Falls back to the campaign's processing_purpose. If the tenant has switched on legal_basis_enforced, a mail without any purpose is refused."
},
"subject": {
"type": "string",
"description": "Subject line"
},
"reply_to": {
"type": "string",
"description": "Reply-to email address"
},
"from_name": {
"type": "string",
"description": "Sender display name"
},
"account_id": {
"type": "string",
"description": "ID of the account (company)"
},
"contact_id": {
"type": "string",
"description": "ID of the contact"
},
"from_email": {
"type": "string",
"description": "Address of a connected mailbox to send from."
},
"to_address": {
"type": "string",
"description": "Recipient email address"
},
"attachments": {
"type": "array",
"items": {
"type": "string"
},
"description": "document_ids"
},
"campaign_id": {
"type": "string",
"description": "ID of the campaign"
},
"attachment_mode": {
"enum": [
"link",
"file"
],
"type": "string",
"description": "link (default) or file"
}
}
},
"annotations": {
"title": "Send email",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:
curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/io.github.toasternet/delegaize"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/io.github.toasternet/delegaize"}) over MCP.
delegate_to_user ~1,757 tokenscreate_lead ~1,192 tokensupdate_lead ~1,092 tokensset_contract_scan_rules ~926 tokenscreate_google_ads_video_campaign ~911 tokensStatic checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).
Operator? Fix these, then re-check live.
Shows whether the server is live and its agent-readiness score; it updates within the hour.
[](https://glimind.com/server/mcp-registry%2Fio.github.toasternet%2Fdelegaize?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fio.github.toasternet%2Fdelegaize?ref=badge"><img src="https://glimind.com/badge/mcp-registry%2Fio.github.toasternet%2Fdelegaize.svg" alt="MCP server status"></a>
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:a9c24e6e25a1564a…, first seen 2026-11-21, included at leaf 374665 of 384,794. Version history · verify what your client received.
Compare: most reliable communication servers · most reliable data servers · most reliable files servers · most reliable marketing servers · most reliable crm servers
Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.
Claude Code
claude mcp add --transport http glimind https://glimind.com/mcp?ref=install-server
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp?ref=install-server"
}
}
}
A free Glimind key lets your agent check whether a server works right now before it calls it, and switch to a live one when it doesn't. No signup, no card.
As of 2026-11-22 16:58 UTC, the DelegAIze MCP server is up (it requires sign-in) with a Glimind reliability score of 90/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks.
DelegAIze MCP server advertises 300+ tools, including add_brevo_contacts_to_list, add_contract_deadline, add_document, add_google_ads_keywords, add_hubspot_activity.
Point your MCP client at this streamable-http endpoint: https://delegaize.innov-ai-tive.de/api/sb/functions/v1/mcp-server
Glimind scanned all 1022 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.
Status page: 90-day uptime, every outage and how long it lasted.
Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.
Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.