raynet-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RAYNET_LOGIN | Yes | The email you sign in to Raynet with | |
| RAYNET_API_KEY | Yes | Your Raynet API key | |
| RAYNET_INSTANCE_NAME | Yes | Your Raynet account name | |
| RAYNET_DEFAULT_OWNER_ID | No | Optional user ID that will own records created by the connector |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| raynet_test_connectionA | Tests the connection to Raynet CRM and returns basic info about the instance |
| raynet_full_scanA | Scans all the main Raynet endpoints (lead, businessCase, company, person, enumerations) and returns a complete mapping of structure, fields, and picklists. Use this when you want to discover the available ID values for statuses, categories, sources, etc. |
| raynet_get_structureB | Fetches the structure of a specific Raynet entity (fields, customFields, picklists) |
| raynet_get_bc_phasesA | Fetches the list of BusinessCase phases (sales pipeline stages) with IDs and names |
| raynet_get_enumerationsB | Fetches all enumerations (picklists) from the Raynet system |
| raynet_searchA | Searches for records in Raynet CRM. Supports field filters, an offset for paging, and free-text search. There is no sorting mechanism — results are always ordered ascending by id (oldest first). Use newest_first to get the most recently created records instead. |
| raynet_get_recordA | Fetches the details of a specific record by ID. A non-existent id is not an error — it returns { found: false, entity, id } (id numbering has gaps, so checking existence this way is expected and normal). A found record returns { found: true, data } with the record's fields in data. |
| raynet_create_lead_fullA | Creates a full pipeline: Company + Person + Lead attached to both. The source and category names are automatically converted to IDs (you don't need to know the IDs!). Use this when you want to add a new client to Raynet in a single call. |
| raynet_convert_lead_to_bcA | Converts an existing Lead into a BusinessCase. The bc_type and bc_phase names are automatically converted to IDs. Use this after 'raynet_create_lead_full' once the client is already interested in the offer. |
| raynet_create_full_pipelineB | ALL IN ONE: creates Company + Person + Lead and optionally converts it into a BusinessCase. One call = the entire sales pipeline in Raynet. All names (source, category, bc_type, bc_phase) are automatically converted to IDs. |
| raynet_update_recordA | Updates a field on an existing lead or businessCase record. Only fields VERIFIED to work against the live Raynet API are supported — see each field's description. Setting businessCasePhase is a manual OVERRIDE of the automated follow-up system, which also moves BCs through phases on its own rules (e.g. deposit paid -> advance phase). After a successful phase change, warn the user that follow-up automation may later re-adjust the phase based on its own rules. Marking a BusinessCase as 'lost' (status + losing reason) is NOT supported by this tool: Raynet's API does not expose those fields for editing at all (confirmed against Raynet's own API spec, not just live testing) — this must be done by hand in the Raynet UI. |
| raynet_delete_recordA | Deletes a record from Raynet CRM (lead, businessCase, company, person). If the record is linked to other data, Raynet will return an error stating what is blocking the deletion. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
The metadata tools overlap substantially: raynet_full_scan, raynet_get_enumerations, raynet_get_structure, and raynet_get_bc_phases all retrieve structural/picklist information, differing mainly in scope. The pipeline-creation tools also overlap, since raynet_create_full_pipeline duplicates raynet_create_lead_full plus raynet_convert_lead_to_bc. Descriptions help, but an agent can still reasonably hesitate between multiple tools.
All tools use the raynet_ prefix and snake_case, which is predictable and readable. Most follow a verb_noun pattern (get_record, update_record, delete_record, create_lead_full), with minor deviations like raynet_full_scan and raynet_search that do not follow the exact convention but remain clear.
Twelve tools is well-scoped for a CRM integration that needs discovery, connection testing, CRUD, search, and pipeline creation. The set is not bloated, and each tool generally maps to a useful operation even if some overlap exists.
Core read, search, delete, and pipeline creation are covered, but update is restricted to lead and businessCase records only, leaving no update path for company or person records. Standalone creation of companies or persons is also absent, since creation is bundled into lead/pipeline flows. These gaps are workable for lead-centric sales workflows but incomplete for full CRM CRUD.