Architecture
The MCP server runs as a standalone service atmcp.remyx.ai. Connect using Streamable HTTP at https://mcp.remyx.ai/mcp, or SSE at https://mcp.remyx.ai/sse for clients that require it.
Every tool calls the engine’s REST API with your own key, so ownership checks and data match the studio exactly. The same tools are also callable over plain HTTP: GET https://mcp.remyx.ai/api/tools lists them, and POST https://mcp.remyx.ai/api/tools/<name> invokes one with a JSON body of its parameters, for scripts that are not MCP clients.
Connecting
Claude Code
Add to your Claude Code MCP configuration (~/.claude/settings.json or project-level):
Claude Desktop
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
Other MCP Clients
Any client supporting the MCP Streamable HTTP transport can connect using the URLhttps://mcp.remyx.ai/mcp with a Bearer token in the Authorization header.
Tools
Parameter tables below are taken from the server’s tool signatures. Optional parameters are marked; everything else is required.Outrider fleet tools
The fleet tool plane mirrors what the studio shows in Agents, Reports, and the Inbox.Research and account
Discovery
get_digest
get_digest
period (today or week, default today), interests (optional list of interest names or ids), limit (per interest, default 5), include_github (default true).Returns: Recommended resources grouped by Research Interest, with titles, abstracts, relevance scores, and links.Example prompt: “Show me this week’s research digest for my retrieval interest”list_interests
list_interests
is_active.get_papers
get_papers
interest (name or id), period (default today), limit (default 10).Returns: Resources matched to the interest with metadata, scores, and Docker availability.refresh_interests
refresh_interests
interests (optional list of names or ids; all active interests if omitted).Returns: Confirmation that the refresh started. Results arrive via get_digest after processing.create_interest
create_interest
name; optional context (the natural-language description Remyx ranks against), daily_count (default 2), is_active (default true), source_repo_url, project_id (a project-mode interest ranks against that project’s experiments), auto_update_from_experiments, included_experiment_ids, and the repo-analysis fields source_repo_metadata, generated_report, repo_analysis.Returns: The created interest with its id and status.update_interest
update_interest
interest_id; optional name, context, daily_count, is_active, source_repo_url, auto_update_from_experiments, included_experiment_ids, and the repo-analysis fields.Returns: The updated interest.Example prompt: “Pause my Long-context retrieval interest” (sets is_active: false)delete_interest
delete_interest
interest_id.list_project_experiments_for_interest
list_project_experiments_for_interest
interest_id.Repo analysis
Generate or refine a Research Interest from a GitHub repository. Remyx profiles the repo and derives the interest context from what the code does.list_github_repos_for_interest
list_github_repos_for_interest
analyze_repo_for_interest
analyze_repo_for_interest
repo_url.Returns: task_id; poll with get_repo_analysis_status.get_repo_analysis_status
get_repo_analysis_status
task_id.Returns: Status, and the generated report plus structured analysis when complete.regenerate_interest_from_repo
regenerate_interest_from_repo
interest_id; optional repo_url to analyze a different repo than the stored source.Returns: task_id; poll with get_repo_analysis_status.Project context
Set a default project once and omitproject_id on later calls. Tools that take a project_id resolve it from this context when the parameter is omitted.
Projects and the quality gate
Experiments
create_experiment
create_experiment
get_experiments
get_experiments
status, resource_id, project_id, interest, limit (20).update_experiment
update_experiment
experiment_id; optional status, outcome, ticket_url, pr_url, pr_status, external_ticket_id, ticket_source, statsig_experiment_id, notes, source_type.log_decision
log_decision
experiment_id, decision (text with reasoning); optional outcome (ship, iterate, abandon).Example prompt: “Log decision on experiment 12: Ship to 100%. It combined retrieval with few-shot selection and produced our best single-experiment improvement.”Relationships: list_experiment_relationships, link_experiment, update_experiment_relationship, unlink_experiment
Relationships: list_experiment_relationships, link_experiment, update_experiment_relationship, unlink_experiment
list_experiment_relationships(experiment_id, direction="both"):in,out, orboth.link_experiment(experiment_id, to_experiment_id, kind, notes?):kindisborrows_from,variant_of,replicates, orreferences.update_experiment_relationship(experiment_id, relationship_id, kind?, notes?).unlink_experiment(experiment_id, relationship_id).
Implementation
get_experiment_context
get_experiment_context
experiment_id.get_reference_implementation
get_reference_implementation
experiment_id.list_active_experiments
list_active_experiments
project_id, limit (20).run_implement_workflow
run_implement_workflow
experiment_id.run_experiment_implementation
run_experiment_implementation
experiment_id.get_implementation_status
get_implementation_status
pipeline_status, PR info, error detail, task_id.Parameters: experiment_id.report_implementation_result
report_implementation_result
experiment_id, pr_url; optional branch_name, summary.Experiment validation (Modal / W&B Launch)
These tools run the experiment-level evaluation path on connected compute (Modal or Weights & Biases Launch) against a locked eval template. They are unrelated to Validate, the PR validation agent, which has no MCP tools and is driven from the PR thread orPOST /validate/runs.
Eval templates: create_eval_template_v2, lock_eval_template
Eval templates: create_eval_template_v2, lock_eval_template
create_eval_template_v2(name, category, project_id?, runtime="lighteval", lighteval_task?, dataset_ref?, variants_schema?, seeds=3, metric_keys?, decision_criteria?, compute_hints?): a draft template with versioning.lock_eval_template(template_id): one-way; a locked template is what runs execute against.
Eval runs: launch_eval_run, get_eval_run, cancel_eval_run, get_eval_run_results
Eval runs: launch_eval_run, get_eval_run, cancel_eval_run, get_eval_run_results
launch_eval_run(experiment_id, github_url, variants (list), template_id?, template_config?, seeds=3, pr_number?, pr_url?): builds the environment, runs the variants on Modal sandboxes, receives results by webhook, and computes a verdict.get_eval_run(run_id): status, results received, verdict so far.cancel_eval_run(run_id): terminates sandboxes and marks the run cancelled.get_eval_run_results(run_id): final aggregated results with a Pass / Warn / Fail verdict.
provision_validation
provision_validation
experiment_id; optional template_name.Returns: A job handle; poll with check_validation_status.check_validation_status
check_validation_status
experiment_id.Returns: Job status and progress.cancel_validation
cancel_validation
experiment_id.get_validation_results
get_validation_results
experiment_id; optional include_raw.update_experiment for now.close_loop
close_loop
experiment_id; optional disposition (shipped, iterating, rejected, abandoned), notify (channel).HTTP-only tools
create_ticket (create a Linear, Jira, or GitHub ticket for an experiment) is registered for the HTTP surface only: POST https://mcp.remyx.ai/api/tools/create_ticket. Every other tool above is available on both.
Slack Agent
The MCP server also powers the managed Slack agent. When you@mention the Remyx bot in Slack, it uses the same tools to respond: fetching digests, listing agents’ output, logging decisions. See Connectors > Slack for setup.
Studio Ask chat
The ✦ Ask button in the studio topbar opens a chat on every page; the Inbox’s Ask and an agent’s Ask about this agent open the same panel scoped to that agent. The panel docks to the right or the bottom, resizes, and minimizes to a pill. Each answer has Copy and, where it proposes work, Start an agent run from this, which hands the proposal to a confirm-gated dispatch. Two backends:- Remyx AI, hosted (the default). Works with nothing connected and answers from the server-assembled context for the agent, run, or Inbox item you opened it from.
- Bring your own provider. Pick a connected Anthropic, Z.ai, or Moonshot AI key to upgrade the chat to a live agent session with the Remyx tool plane. The choice is remembered in your browser; unconnected providers stay visible but disabled.
trigger_agent_run, pause_agent, install_agent, fork_repo) are deliberately absent: the chat proposes those actions in text, and the studio’s confirm-gated buttons execute them through the engine. A turn that fails on a transient error is retried, up to three attempts.
Implementation Pipeline
For research-sourced experiments with a launch context, a connected coding agent can run the full implementation flow:- Fetch the experiment context (resource metadata, Docker environment, repo structure, implementation plan)
- Read the target repository
- Generate code changes implementing the technique
- Push a branch and open a PR
- Link the PR back to the experiment