Carta MCP server icon

Carta

by Carta

Finance9 tools

Query cap table ownership, 409A valuations, SAFEs, vesting schedules and fund performance from your AI assistant. Anthropic's directory labels this connector Read — three independent checks say otherwise, and the nine listed tools are a dispatcher facade over a much larger command surface.

Verified connector

Listed by Anthropic as a partner connector in its Connectors Directory.

Connection checked by Agentman on .

Anthropic states this reflects the level of review a connector received, not a security audit.

Connect Carta via MCP

https://mcp.app.carta.com/mcp

Works in any MCP-compatible client. In Agentman Studio it is one click — no config file to edit.

Carta Tools & Capabilities (9)

Tool names from Anthropic's directory listing. This server requires sign-in, so we could not read tool descriptions or parameter schemas.

Limits

  • The directory's "Read" label is incomplete. Three readwrite_ OAuth scopes are advertised, Carta's CRM guide states the plugin writes, and a published Carta skill issues securities. Two of the three plugins are genuinely read-only; the connector as a whole is not.
  • Nine is not the tool count. Three of the nine listed names are dispatchers over a command registry, and Carta's own skills call tools — call_tool, search_tools, mutate — that the directory never lists. The true surface is unenumerable without authenticating.
  • The server is stateful and the active context is not readable. set_context selects a fund administration firm for later calls, the model may change it at any turn, and no tool reports which firm is currently active. A wrong-context answer is possible and would not announce itself.
  • Carta documents nothing about contexts. None of the four published guides mentions contexts, context switching, or a login spanning several firms. The discipline exists only inside plugin skill files, and does not reach a client connecting with the bare URL.
  • cap_table_healthcheck provenance is unresolved. The tool appears in Anthropic's snapshot and in none of Carta's documentation or public source. Whether its output is a retrieved Carta report or a generated assessment is unknown, and an assessment of a company's equity structure is a materially different artefact from a report.
  • welcome and cap_table_chart are likewise undocumented by name. Carta's skills describe a once-per-connection handshake that caches identity and firm data for 24 hours, but no vendor documentation ties that behaviour to the listed tool.
  • No tool is annotated. The endpoint returned 401 to an anonymous request on 2026-08-19, so no inputSchema, readOnlyHint or destructiveHint was readable for any of the nine.
  • The read surface reaches named individuals' equity records. Stakeholder lists, grants with vesting schedules, and witness and spousal-consent signature status all identify third parties who did not choose the AI client.
  • Investor tools need Fund Admin, and the gate is enforced. Carta's connection handshake returns an is_fund_admin_user flag and its own skill stops when it is false.
  • Only one RFC 9728 path form works. The root and path-insert forms both 404. A metadata check that tries only the conventional root form would wrongly report no descriptor.
  • Carta collects plugin telemetry. Its investors documentation states the plugin collects session context, model configuration and plugin activity to improve reliability, and directs readers to its privacy policy.
  • Prompts are unconfirmed. Anthropic's 2026-08-16 snapshot lists an empty prompt_names array, and the gated endpoint blocked our own check.

Frequently asked questions

Is the Carta MCP server read-only?

No. Anthropic's directory labels it Read, but three checks disagree. The OAuth descriptor advertises three readwrite scopes alongside three read scopes; Carta's own CRM guide states the plugin supports both read and write; and a published skill issues stock certificates and option grants through a mutate call. Cap table and fund queries are read-only — the connector as a whole is not.

What is a context in the Carta MCP server, and can Claude switch it mid-conversation?

A context is a fund administration firm. list_contexts enumerates the firms your login can reach and set_context switches the active one, so a model can change it at any point in a conversation. Carta's published skills instruct the model to infer the intended firm from the request and only ask when it cannot choose confidently. Nothing displays the active context alongside an answer.

Does the Carta MCP server have only nine tools?

No — nine is the dispatcher facade. Three of the listed names are generic dispatchers: discover enumerates a command registry, fetch retrieves through it, and Carta's own skills reference call_tool, search_tools and mutate. The registry holds named commands such as a stakeholders lookup and a feedback writer. The real surface is far larger than nine and Anthropic's listing cannot show it.

What does the Carta cap table connector actually reach?

Individual stakeholder records. Carta documents access to stakeholder lists, ownership by share class, option grants with vesting schedules and cliff dates, SAFEs, convertible notes, 409A valuations, financing history and witness or spousal consent signature status. Those records identify named employees, founders and investors who are third parties to the person connecting. The connector adds no new access, only a new destination.

Which Carta plan and role do you need to use the MCP server?

It depends which plugin you want. Cap table access needs a Carta cap table account; investor tools require a Fund Administration subscription, which Carta gates on an is_fund_admin_user flag returned at connection. On Claude Team and Enterprise plans only an Owner can add the connector, after which members authenticate individually. Pro and Max users install it themselves.

Does cap_table_healthcheck retrieve a report or generate an assessment?

Neither is documented. The tool name appears in Anthropic's directory snapshot and nowhere in Carta's documentation or its public plugin repository, so whether it returns a retrieved Carta report or a computed assessment is unresolved. A related published skill detects expiring 409As and low option pools, and Carta gates AI computation behind an explicit user prompt — but that skill is not this tool.

Sources

  • Setting up Carta Plugins — https://docs.carta.com/api-platform/docs/claude-plugins-setup (fetched 2026-08-19 as markdown via the .md suffix the site advertises; page updatedAt 2026-08-18. Source of the three-plugin structure, the shared endpoint, the Owner-only admin gate on Team and Enterprise, the Pro and Max personal path, the Claude Code and ChatGPT Work instructions, the GitHub marketplace route, the troubleshooting notes on Fund Admin data sharing, and the statement that financial data flows through Claude) · retrieved 2026-08-19
  • Carta Cap Table guide — https://docs.carta.com/api-platform/docs/carta-cap-table (fetched 2026-08-19; page updatedAt 2026-06-02. Source of the read surface — stakeholders, share classes, voting power, SAFEs, convertible notes, option pools, grants and vesting, 409A valuations, financing history and compensation benchmarks — the read-only statement for this plugin, the modelling capabilities, and the permissions-and-access section) · retrieved 2026-08-19
  • Carta Investors guide — https://docs.carta.com/api-platform/docs/carta-investors (fetched 2026-08-19; page updatedAt per site header. Source of the read-only statement, the SELECT-only warehouse query description, the Form ADV point-in-time and entity-coverage limitations, the local-Excel-output statement, the firm-scoping statement, and the tearsheet and query-performance caveats) · retrieved 2026-08-19
  • Carta CRM guide — https://docs.carta.com/api-platform/docs/carta-crm (fetched 2026-08-19; page updatedAt 2026-07-28. Source of the read-and-write statement, the create-and-update record list, the firm-scoping statement, and the confirmation-before-ambiguous-writes statement) · retrieved 2026-08-19
  • Carta public plugin sources — https://github.com/carta/plugins (fetched 2026-08-19 via the GitHub API and a shallow clone; repository last updated 2026-08-20. Source of the dispatcher evidence, the carta-issuance and carta-witness-signatures skills, the context-versus-corporation rule and its incident log, the inference-first firm selection guidance, the show-and-confirm instruction, the is_fund_admin_user gate, the AI computation gate, the 24-hour handshake cache, and the telemetry statement) · retrieved 2026-08-19
  • Live RFC 9728 protected-resource descriptor — https://mcp.app.carta.com/.well-known/oauth-protected-resource/mcp (fetched 2026-08-19; 200, application/json, 295 bytes, eight scopes of which three are readwrite_. The root form and the path-insert form both return 404 with a 9-byte text/plain body) · retrieved 2026-08-19
  • Live RFC 8414 authorization-server metadata — https://mcp.app.carta.com/.well-known/oauth-authorization-server (fetched 2026-08-19; 200, issuer https://mcp.app.carta.com/, registration_endpoint, revocation_endpoint, PKCE S256, two grant types, client_id_metadata_document_supported, and a scopes_supported list identical to the protected resource's. The path-append form and /.well-known/openid-configuration both 404) · retrieved 2026-08-19
  • Anonymous initialize probe of https://mcp.app.carta.com/mcp (2026-08-19; HTTP 401 with a JSON invalid_token body and a www-authenticate challenge naming the path-append resource_metadata URL. No authentication was attempted and no tool was called) · retrieved 2026-08-19
  • Carta documentation robots.txt — https://docs.carta.com/robots.txt (fetched 2026-08-19; 200, allows all agents, disallows only edit, login and CDN paths, and carries no Content-Signal directives. A root llms.txt returns 404; the index is published at /api-platform/llms.txt) · retrieved 2026-08-19
  • Anthropic connector directory — https://claude.ai/directory/4b463f8b-6db0-4d0e-9693-8b39f37e4447 (snapshot 2026-08-16; source of the nine tool_names, the empty prompt_names array, the "Read" permissions label, the free-text description quoted in summary, the partner tier, the financial-services category and the documentation URL) · retrieved 2026-08-16

Use in Agentman

Connect once and your agents call these tools on their own — on a schedule, in a workflow, with nobody at the keyboard.

Open in Agentman Studio

Server Info

Category
Finance
Developer
Carta
Tools
9
Domain
mcp.app.carta.com

Using Claude Desktop or another MCP client? Setup docs — the connection URL above works anywhere.