Keywords AI MCP server: 67 tools, renamed Respan

The product changed name, and the connector is large. What its ten tool groups cover, and the header that registers only the tools you name.

Checked 6 October 2026 · from The vendor's own MCP documentation and its open-source server, published under the Respan name

One of 91 guides to monitoring and developer tools. Each covers what an AI coding agent can get out of the tool through MCP, the protocol that lets the agent query the tool directly.

What is the Keywords AI MCP server?

It is Respan's server for the Model Context Protocol. The product traces language-model calls and evaluates them, so a connected agent reaches both the traffic and the scoring.

The reading surface is the useful half for most sessions. list_logs and get_log_detail cover request history, while list_traces and get_trace_tree cover structure and get_spans_summary aggregates spans.

The authoring half covers prompt versions, evaluators and workflows, which most observability connectors do not expose. Prompts have versions that can be created and deployed, and evaluators and workflows have their own commit tools.

It is strongest in agent observability, touches cost through logged usage, and reaches nothing in code review or CI.

For an agent, that means Respan answers what your model calls did, what they scored and what they cost. It can also deploy the next prompt version. It sees nothing outside model traffic, so a service question needs a separate connector.

What can an AI agent do with Keywords AI?

Decide the tool scope before the first session. With 67 tools registered by default, the Respan-Enabled-Tools header is the difference between a focused connection and a large one.

What the tool definitions cost in context

A client that loads every tool definition at the start of a session spends this much context before the first question. Claude Code defers definitions by default through tool search, and loads a tool's definition when the agent needs it. The method below gives the version and date measured.

A context window is the amount of text a model can hold at once. On 24 August 2026, the 55 documented tools cost 2,815 to 3,407 tokens on Claude with the whole surface loaded. Each description was one short line. The server now registers 67 tools, so a full session today costs more.

The Respan-Enabled-Tools header narrows the set to named tools, so a scoped session pays less. The 24 August figure is also a floor, because it counts names and descriptions only.

Encodings: GPT-5.6, GPT-5.5 o200k_base; GPT-4, GPT-3.5 cl100k_base; Claude Haiku 4.5 to Opus 5 count_tokens. Counted from the 55 tool entries in the vendor's own documentation on 24 August 2026.

The hosted server returned 401 to an unauthenticated tools/list, so no input schemas were counted. These figures cover each tool's name and description only. They are a floor.

The Claude columns are measured through the API's count_tokens endpoint, with an empty schema per tool. So they cover the same content as the GPT columns. The range there is two tokenizer generations. Haiku 4.5 and Opus 4.6 sit at the low end. Opus 5 and Sonnet 5 sit at the high end. The gap between them is about a fifth.

Can Keywords AI watch your own AI agents?

It is the most complete agent-observability surface measured across these vendor guides, with only cost left partial. Read from the server source on 6 October 2026.

Keywords AI MCP server limits: where answers come back incomplete

Keywords AI starts with a large default surface and a changed brand; those two facts shape the limits below.

How to configure Keywords AI MCP for agents

1. 1

   Whitelist the tools you need

   Respan-Enabled-Tools takes a comma-separated list of exact tool names; without it, all 67 are available.

2. 2

   Uncheck Write for a read-only session

   An API key carries Read, Write and Gateway permissions, and a key without Write keeps the agent to reads.

3. 3

   Pick the credential by scope

   An API key reaches only the project it was created in. OAuth acts as you in your active organization, and the organization tools need it.

4. 4

   Decide who may deploy

   deploy_prompt_version changes what production serves, and deploy_workflow makes a committed workflow version live.

5. 5

   Know the name

   Everything is published as Respan, so searching for Keywords AI documentation will send you in circles.

Paste this into your agent’s instructions

Deployment tools sit in the same list as reading tools, and the tool scope can differ per connection. Both belong in the answer.

When you answer using Respan MCP tools, state:
- The project and period the answer covers.
- Whether the session was scoped with Respan-Enabled-Tools,
  and which tools were enabled.
- Whether you deployed anything. deploy_prompt_version
  changes what production serves.
Never state that data does not exist. State that no logs or
traces matched the filters above.
Write your answer in ASD-STE100 Simplified Technical
English. Use short sentences with one idea in each.

Do you need the MCP server at all?

Not for a scheduled export. Respan has a REST API, and for that job it avoids both the context cost and the write surface.

The connector earns its place when the loop is short: read the failing trace, adjust the prompt version, and evaluate it without leaving the editor.

For tracing alone, Langfuse and Arize Phoenix cover that ground with narrower connectors.

Connect a scoped session for prompt and evaluation work. Use the API for reporting.

Keywords AI MCP server setup

The server is hosted, so nothing is installed. The documentation starts with an API key, passed as a bearer token. Uncheck Write on the key for a read-only connection.

OAuth sign-in works without a key and acts as you in your active organization.

Respan Enterprise uses https://mcp.respan.ai/mcp/enterprise in place of the platform URL. A separate docs server at https://mcp.respan.ai/mcp/docs has one tool, search_docs, and needs no key.

claude mcp add --transport http respan \
  https://mcp.respan.ai/mcp \
  --header "Authorization: Bearer <your-respan-api-key>"

{"mcpServers":{"respan":{
  "url":"https://mcp.respan.ai/mcp",
  "headers":{"Authorization":"Bearer <your-respan-api-key>"}}}}

[mcp_servers.respan]
url = "https://mcp.respan.ai/mcp"
headers = { Authorization = "Bearer <your-respan-api-key>" }

Every other client

Each block below is the configuration for one client, with the file path and the key that client expects.

{"mcpServers":{"respan":{"url":"https://mcp.respan.ai/mcp",
  "headers":{"Authorization":"Bearer <your-respan-api-key>"}}}}

{"mcpServers":{"respan":{"url":"https://mcp.respan.ai/mcp",
  "headers":{"Authorization":"Bearer <your-respan-api-key>"}}}}

{"servers":{"respan":{"url":"https://mcp.respan.ai/mcp",
  "headers":{"Authorization":"Bearer <your-respan-api-key>"}}}}

{"mcpServers":{"respan":{"url":"https://mcp.respan.ai/mcp",
  "headers":{"Authorization":"Bearer <your-respan-api-key>"}}}}

claude mcp add --transport http respan \
  https://mcp.respan.ai/mcp \
  --header "Authorization: Bearer <your-respan-api-key>" \
  --header "Respan-Enabled-Tools: list_logs,get_log_detail"

Read-only access, permissions and security

• Prompts, prompt versions, evaluators, pipelines, workflows and datasets can all be created or changed

  34 of the 67 tools write, run or deploy.

• Three tools change what runs live

  deploy_prompt_version changes what production serves, and deploy_workflow and undeploy_workflow start or stop a workflow.

• Deletion is reachable

  delete_evaluator, delete_dataset, delete_experiment and delete_workflow all register by default. remove_dataset_logs can wipe a dataset's contents.

• A read-only key is available

  An API key with Write unchecked keeps the agent to reads, whatever the enabled-tools header says.

• Traces carry prompt content

  A trace tree includes the model calls it describes, so that content reaches the model reading it.

Troubleshooting

The endpoint returns 401

An unauthenticated request is rejected with an Unauthorized error. Pass the API key as a bearer token, or complete OAuth.

Documentation cannot be found under Keywords AI

The product is published as Respan. The MCP documentation lives under the Respan domain rather than the original brand.

All 67 tools appear in the client

All 67 tools register unless narrowed. Add the Respan-Enabled-Tools header with the exact tool names you want.

Production behavior changed after a session

Check for a deployment. deploy_prompt_version is in the default tool list.

Keywords AI MCP server: Reference

What engineers report

The server source is public, so the counts below come from its own registration calls.

Tool inventory read from respanai/respan-mcp on 6 October 2026. Authentication routes, endpoints and the scoping header read from the vendor's MCP documentation, published under the Respan name, the same day. An unauthenticated tools/list against mcp.respan.ai/mcp returned 401 on 6 October 2026.

Should you connect an agent to Keywords AI?

Yes. Best for a scoped enabled-tools list per session, with deploy_prompt_version left out unless deploying is intended.

Strongest fit

Teams already tracing model calls with this platform who want prompt and evaluation work inside the editor.

Main advantage

A documented header for registering only the tools a session needs, plus a read-only API key, which few connectors here provide.

Main weakness

The rename means most existing references point at a brand the documentation no longer uses.

Operational risk

Deployment and deletion tools register by default alongside the reading ones.

Frequently asked questions