Revensi MCP server

• Registry namecom.revensi/revensiverified in the MCP registry

The registry name sits under revensi.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-25
• Tools12
• Server calls itselfrevensi
• Server version2.1.0
• Protocol version2025-06-18

On 2026-10-25 the server answered initialize and tools/list without a sign-in. First answer in 778 ms.

• Whether its tools do the product's job has not been judged yet.
• Checked on 4 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
• Answeredmeasuring4 of the 7 daily checks it takes to print a share
• Median first answer229 ms
• Space in an agent's context≈ 3,547 tokensthe definitions of all its tools (12), which an agent carries on every turn
• Tool definitionsB · 83 of 100
• Typed results12 of 12 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 12 of 12

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• search_agents

  Search Revensi's free published agent blueprints by task, department, system or integration. No account or authentication is needed. These are specifications and fictional examples, not connected or running agents.

• get_agent

  Read the full published blueprint, including inputs, outputs, tools, context, deliverables, review boundaries, evaluations and fictional examples. No authentication needed. Does not execute an agent or grant access to external systems.

• get_agent_spec

  Get a published agent's Markdown build brief to adapt to the user's systems. No authentication needed. This returns a specification; it does not create, connect or run the agent.

• list_workflows

  Use this when the user wants to find or compare saved workflows in their Revensi workspace. Returns live workspace data, not an interview transcript.

• get_workflow

  Use this when the user wants one saved workflow's map, effort, scores, and open questions. Never returns the interview transcript.

• list_workflow_questions

  Use this when the user wants unanswered or deferred questions and blockers from active, non-archived Revensi workflows. This tool does not answer them.

• list_connectors

  Use this when the user wants named services in the Revensi connector catalog and which workflow maps mention them. These are catalog records, not authenticated external accounts.

• list_resources

  Use this when the user wants metadata for files saved in their Revensi resource library. Does not return document bodies.

• add_workflow

  Use this only after the user reviews and approves a complete conversation-drafted workflow. Creates one draft; it does not publish or run the workflow.

• add_connector

  Use this when the user wants to name an external service in Revensi's connector catalog. This does not connect an account or grant access.

• remove_connector

  Use this only after the user clearly asks to remove the exact named catalog entry. Refuses entries still referenced by any workflow; does not disconnect external accounts.

• remove_resource

  Use this only after the user confirms the exact named resource. Deletes its library copy and searchable chunks; historical workflow quotations may remain.