Provider REST API

16 actions

Connect Claude to Langfuse

Read LLM traces, scores, prompts and datasets, and score or label them, in Langfuse Cloud or a self-hosted Langfuse. Toolspoke puts 16 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: Public and secret key
Actions exposed: 16
What a call bills: Nothing
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Langfuse
Open the marketplace in your workspace, add Langfuse to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with public and secret key. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Langfuse shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Langfuse asks for

Public and secret key. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

Public key and secret keyRequired: Langfuse → your project → Settings → API Keys → Create new API keys. Paste the public key, a colon, then the secret key, with no spaces. A key pair reaches exactly one project.; pk-lf-…:sk-lf-…
Langfuse hostOptional: https://cloud.langfuse.com for EU cloud, https://us.cloud.langfuse.com for US cloud, https://jp.cloud.langfuse.com for Japan, or the URL of your self-hosted Langfuse. No path.; https://cloud.langfuse.com

What Claude can do in Langfuse

16 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 10Reads
Writes: 4Writes
Destructive: 2Destructive

Reads

Fetches data and changes nothing.

list_projects
Return the project this key pair belongs to, with its id, name and retention. Takes no arguments, and it fails when the keys are wrong or the host is the wrong region, which is why an install tests itself with it.
list_observations
List observations (spans, generations, events, tool calls) newest first, filtered by trace, session, user, name, type or level and a start-time window. This is how to read a trace: pass trace_id. Cursor-paginated; pass the returned cursor to get the next page. The io field group returns prompts and completions, which are your users' content.
query_metrics
Aggregate observations or scores: counts, latency, token use and cost, grouped by dimensions and optionally bucketed over time. Real-time. Example: view observations, dimensions [{"field":"name"}], metrics [{"measure":"totalCost","aggregation":"sum"}]. High-cardinality dimensions such as ids are refused with a 400.
list_scores
List scores (evaluations, user feedback, annotations) newest first, filtered by name, source, trace, session or time. Cursor-paginated. Add fields=details for comments and metadata.
list_prompts
List prompts in the project by name, with their versions, labels and tags. Filter by name, label (e.g. production) or tag.
get_prompt
Fetch one prompt's text or chat messages and its config. Without version or label you get the version labelled production.
list_datasets
List the datasets in the project, used for experiments and evaluations.
get_dataset
Fetch one dataset by name, with its description and metadata.
list_dataset_items
List the items in a dataset - inputs and expected outputs, often copied from production traces.
list_comments
List comments people left on traces, observations, sessions or prompts. Filter by object to read the discussion on one trace.

Writes

Creates or updates something on the other side.

create_score
Attach a score to a trace, observation or session - an evaluation result, a label, or a user's thumbs up. Supply the trace_id (plus observation_id to score one step) or a session_id. The score appears in the API after a short delay.
create_text_prompt
Create a text prompt, or a new version of one if the name exists. Versions are immutable and old ones stay, so this is not destructive. Be careful with labels: putting production on the new version makes every application that fetches the production label serve it.
update_prompt_labels
Set the labels on one prompt version. This is how a version is promoted (add production) or rolled back (move production to an older version). It changes what applications serve at once, but the previous state can be restored with another call.
create_dataset_item
Add an item to a dataset, or replace one by passing its id. Link it to the trace it came from with source_trace_id.

Destructive

Deletes or permanently alters something. Worth granting on purpose.

delete_score
Delete one score permanently. There is no undo, and evaluation dashboards built on it change.
delete_trace
Delete one trace and its observations and scores permanently. Use it to remove data that should never have been logged. There is no undo.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 16 actions above are the whole of it. A call to any other name is refused before it reaches Langfuse rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
It reaches no further than your credential: Toolspoke holds no access to Langfuse of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Langfuse: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Langfuse. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Langfuse's own rate limits. A call that Langfuse refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Langfuse?

16 named actions: 10 that only read, 4 that write and 2 that delete or permanently alter something. They include list_projects, list_observations and query_metrics. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Langfuse connector need?

Public and secret key. The connector asks for public key and secret key, and optionally langfuse host. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Langfuse connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 16 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Langfuse connector not do?

The 16 actions above are the whole of it. A call to any other name is refused before it reaches Langfuse rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Toolspoke holds no access to Langfuse of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Langfuse. An agent has to ask. Toolspoke does not retry, queue or back off around Langfuse's own rate limits. A call that Langfuse refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Langfuse's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Langfuse?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and what the call cost in sandbox time and model tokens. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More observability connectors

Browse all of them