A side-by-side look at the E Arveldaja MCP and Figma MCP Rust MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose E Arveldaja MCP for finance & fintech work as a local process; choose Figma MCP Rust for finance & fintech as a local process. You can also run both side by side in one mcpServers block.
get_setup_instructions, get_server_status, import_apikey_credentials.get_document, get_pages, get_metadata.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Finance & Fintech | Finance & Fintech |
| Quality signal | 67/100 · Great | 67/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 39 | 68 |
| Directory activity | 2 views 0 installs 0 upvotes | 4 views 0 installs 0 upvotes |
| Tools | 130 | 73 |
| Full listing | View E Arveldaja MCP | View Figma MCP Rust |
get_setup_instructionsShow how to configure e-arveldaja API credentials when the server is running without connections.get_server_statusReport the running e-arveldaja MCP server version, the active tool profile, and any active point-of-use release notices. Read-only; needs no credentials.import_apikey_credentialsPreview and persist apikey*.txt credentials into local/global .env. Preview-first: the default call verifies and projects the target and returns a plan_handle; call again with execute=true and that handle to persist. overwrite=false appends different credentials as another connection.list_stored_credentialsInspect credentials stored in local/global .env files.remove_stored_credentialsPreview and remove one stored credential block from a local/global .env file. Preview-first: the default call projects the removal and returns a plan_handle; call again with execute=true and that handle to delete.list_connectionsList configured e-arveldaja connections and the active index.switch_connectionSwitch active e-arveldaja connection. Clears caches; interrupted in-flight tools are blocked from further API requests.clear_cacheClear cached e-arveldaja API and reference data. Use after changing data directly in the e-arveldaja web UI, or before reports that must reflect the latest upstream state.get_session_logRetrieve mutating-operation audit log Markdown for the current connection, another audit-log label, or connection:<raw name>.list_audit_logsList available human-readable audit log files.clear_session_logClear the audit log for the current connection. DESTRUCTIVE — cannot be undone.list_clientsList clients. Paginated. Brief view by default; use view='full' or get_client for detail.get_documentGet the full node tree of the current page (not the whole file — only the active page). Returns all nodes recursively and can be very large. Prefer get_design_context for exploration or when token efficiency matters.get_pagesList all pages in the document with their IDs and names. Lightweight alternative to get_document.get_metadataGet metadata about the current Figma document: file name, pages, current page.get_selectionGet the nodes currently selected in Figma. Returns an empty array if nothing is selected. Use get_design_context or get_node to retrieve deeper detail about a specific node by ID.get_nodeGet a single node by ID with full detail. Use get_nodes_info to fetch multiple nodes in one round-trip instead of calling this repeatedly. Node ID must be colon format e.g. '4029:12345', never hyphens.get_nodes_infoGet full details for multiple nodes by ID in one round-trip. Prefer this over calling get_node repeatedly when you need several nodes.get_design_contextGet a depth-limited, token-efficient tree of the current selection or page. Use this instead of get_document when exploring large files. Supports detail levels (minimal/compact/full) and dedupe_components for pages heavy with repeated component instances.search_nodesSearch for nodes by name substring and/or type within a subtree. Use this when you know (part of) the node name. Use scan_nodes_by_types when you want all nodes of a type regardless of name.scan_text_nodesScan all TEXT nodes in a subtree and return their content. Shorthand for scan_nodes_by_types with ['TEXT'] — use when you only need text copy from a component or frame.scan_nodes_by_typesFind all nodes of specific types in a subtree, regardless of name. Use search_nodes instead when you need to filter by name.get_reactionsGet the prototype reactions defined on a node. Returns an array of reaction objects — each has a trigger (e.g. ON_CLICK, ON_HOVER, AFTER_TIMEOUT) and an actions array (navigate to node, open URL, go back, etc.). Use set_reactions to add or replace reactions, remove_reactions to delete them.get_viewportGet the current Figma viewport: scroll center, zoom level, and visible bounds.Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
{
"mcpServers": {
"e-arveldaja-mcp": {
"command": "npx",
"args": [
"-y",
"e-arveldaja-mcp"
]
}
}
}
{
"mcpServers": {
"figma-mcp-rust": {
"command": "npx",
"args": [
"-y",
"@alvinindra/figma-mcp-rust@latest"
]
}
}
}