BROWSER USE - Browser Use Agents: give Browser Use a task and receive completed work. API V4 is current for new integrations. - Browser Infrastructure: connect your agent or automation to managed browsers through SDK, REST, or CDP. Starts at $0.02/browser-hour. - Developer tools: Open Source, Browser Harness, SDK, and MCP support the two products above. [Developer Index](https://browser-use.com/index.md) [Product Map](https://browser-use.com/llms.txt) [Full Product Context](https://browser-use.com/llms-full.txt) [Pricing](https://browser-use.com/pricing.md) [Cloud Docs](https://docs.browser-use.com/cloud/quickstart) [Open Source Docs](https://docs.browser-use.com/open-source/introduction) --- # Potter's Wheel: 37 WebMCP tools for AI agents ![](https://www.google.com/s2/favicons?domain=shiv-aurora.github.io&sz=96) Education & health · shiv-aurora.github.io ## Potter's Wheel Research manuscript workspace tracking claim provenance. Agents can read claims and evidence, verify claims and stage reviewed text changes. [Open shiv-aurora.github.io](https://shiv-aurora.github.io/openai-webmcp-challenge/) ## Ask an agent to - Verify the selected claim against its linked evidence - Attach this experiment run as evidence for a figure - List claims that still need review ## 37 tools - `add_experiment_metric`untrusted content Add or update a named metric on a research run. experimentId: string, key: string, value - `add_experiment_parameter`untrusted content Add or update a named configuration value on a research run. experimentId: string, key: string, value - `attach_evidence`untrusted content Attach structured evidence to the selected or explicitly identified tracked manuscript object. This visibly updates the same provenance state shown in the integrity panel. objectId: string?, type: string?, label: string, artifactId: string?, experimentId: string?, commit: string?, metric: string?, uri: string?, … (list cut; the site may define more) - `attach_experiment_artifact`untrusted content Attach a result, figure, table, configuration, or other artifact to a research run. experimentId: string, label: string, type: string?, uri: string?, id: string? - `compare_experiments`read-onlyuntrusted content Compare the configuration, metrics, datasets, artifacts, and provenance impact of two experiment runs. baseExperimentId: string, candidateExperimentId: string - `create_claim`untrusted content Create a first-class provenance claim from the researcher's current explicit text selection. Requires the exact text previously read by the agent so stale selections fail safely. expectedText: string - `create_experiment`untrusted content Create a run in the same Experiments workspace the researcher uses. id: string?, name: string, status: string?, method: string?, sourceCommit: string?, notes: string?, startedAt: string? - `create_experiment_evidence`untrusted content Turn a run metric, configuration, result, figure, or table artifact into durable evidence for the paper. A superseded evidence id rewires its manuscript links and creates Research Diffs. experimentId: string, label: string, type: string?, evidenceKind: string?, metric: string?, value?, baseline?, artifactId: string?, … (list cut; the site may define more) - `get_claim`read-onlyuntrusted content Return the currently selected claim, or a tracked claim by id, including its verification state and linked evidence. claimId: string? - `get_current_section`read-onlyuntrusted content Return the named manuscript section containing the researcher's current selection together with that section's live text. - `get_current_selection`read-onlyuntrusted content Return the researcher's live manuscript selection, section, object kind, and verification state without changing the document. - `get_evidence_catalog`read-onlyuntrusted content Return evidence between experiments and the paper, including its originating run and manuscript usage. experimentId: string?, type: string? - `get_experiment`read-onlyuntrusted content Return one run with its parameters, metrics, artifacts, produced evidence, and dependent manuscript objects. experimentId: string - `get_experiments`read-onlyuntrusted content Return the same persisted experiment runs visible in Potter’s Wheel, optionally filtered by run status. status: string?, limit: integer? - `get_figure`read-onlyuntrusted content Return the currently selected figure, or a tracked figure by id, including its verification state and linked evidence. figureId: string? - `get_integrity_status`read-onlyuntrusted content Return live manuscript integrity counts and optional summaries of tracked provenance objects without changing researcher state. includeObjects: boolean?, limit: integer? - `get_manuscript_context`read-onlyuntrusted content Return live manuscript text and integrity context for the current selection, current section, or manuscript. scope: string?, maxChars: integer? - `get_navigation_targets`read-onlyuntrusted content List tracked manuscript objects that an agent may ask the researcher to inspect or navigate to, optionally filtered by object kind or verification state. kind: string?, verificationState: string?, limit: integer? - `get_provenance`read-onlyuntrusted content Return provenance and linked evidence for the currently selected tracked manuscript object, or for an explicit object id. objectId: string? - `get_research_diffs`read-onlyuntrusted content Return evidence-driven Research Diff entries from live provenance alongside currently pending CriticMarkup manuscript proposals. - `get_table`read-onlyuntrusted content Return the currently selected table, or a tracked table by id, including its verification state and linked evidence. tableId: string? - `insert_comment`untrusted content Insert an additive visible comment on the current selection line or a tracked object's line. Existing comment threads are never overwritten; the tool fails if that line already has a comment. text: string, objectId: string?, line: integer? - `link_evidence_to_manuscript`untrusted content Connect existing experiment evidence to an existing claim, figure, table, or method in the same visible workspace. evidenceId: string, objectId: string, relation: string? - `log_experiment_metric_point`untrusted content Append a numeric metric point at a training step and update the run's latest value, like an MLflow metric history. experimentId: string, key: string, value: number, step: number? - `navigate_to_object`untrusted content Move the visible editor selection to a tracked claim, method, figure, or table. This changes navigation state only; it does not modify manuscript or provenance content. objectId: string - `navigate_to_research_diff`untrusted content Move the visible editor selection to an evidence-driven Research Diff or pending CriticMarkup proposal so the researcher can inspect it without changing manuscript content. from: integer?, diffId: string? - `propose_claim_change`untrusted content Stage a replacement for a tracked claim as CriticMarkup. This never silently accepts the new manuscript text: the researcher receives the editor's normal accept/reject controls. claimId: string?, expectedText: string, replacementText: string - `record_verification_result`untrusted content Record an evidence-backed conclusion from an external research agent on a tracked claim. This stores the visible result and reasons but never changes manuscript text; use propose\_claim\_change separately for a… claimId: string?, outcome: string, reason: string, evidenceIds: array - `replace_selected_content`untrusted content Stage a replacement for the researcher's current explicit selection. Despite the action name, the new text is not silently accepted: it is inserted as CriticMarkup and remains pending until the researcher accepts or… expectedText: string, replacementText: string - `review_research_diff`untrusted content Record a defer or reject decision for an evidence-driven Research Diff without changing manuscript text. Agents cannot accept manuscript rewrites. diffId: string, decision: string, reason: string? - `set_experiment_status`untrusted content Mark a run planned, running, completed, or failed in the shared experiment workspace. experimentId: string, status: string, completedAt: string? - `set_verification_state`untrusted content Set the verification state of a tracked manuscript object. Verified, stale, contradicted, and needs-review states require linked evidence; unlinked is only valid when no evidence is attached. objectId: string?, verificationState: string - `stage_research_diff`untrusted content Stage the proposed manuscript text for one evidence-driven Research Diff as CriticMarkup. The update remains unapplied until the researcher uses the visible accept/reject controls. diffId: string - `supersede_experiment`untrusted content Identify a newer run as replacing an earlier run and mark dependent manuscript objects stale for review. olderExperimentId: string, newerExperimentId: string - `update_evidence`untrusted content Update structured evidence already linked to a tracked manuscript object. The evidence must belong to that object; unrelated evidence cannot be edited through this call. objectId: string?, evidenceId: string, type: string?, label: string?, artifactId: string?, experimentId: string?, commit: string?, metric: string?, … (list cut; the site may define more) - `update_experiment`untrusted content Update run metadata such as its name, method, notes, timestamps, datasets, or source commit. experimentId: string, name: string?, method: string?, sourceCommit: string?, notes: string?, datasets: array?, startedAt: string?, completedAt: string?, … (list cut; the site may define more) - `verify_claim`untrusted content Run the editor's deterministic Verify This comparison for a selected or identified tracked claim. It compares only unambiguous manuscript and evidence metric values and returns an honest review-required outcome… claimId: string? Tools 37 Registered with JavaScript Scan finished Oct 19, 2026 Tool names and descriptions are what shiv-aurora.github.io/openai-webmcp-challenge/ registered when we loaded it in Chrome 154 on Browser Use Cloud. The summary and the “ask an agent” lines are AI-written from them. To call the tools yourself, see [Chrome’s WebMCP docs](https://developer.chrome.com/docs/ai/webmcp). [How we found it](https://browser-use.com/webmcp#method). ## More education & health sites - [![](https://www.google.com/s2/favicons?domain=gla.ac.uk&sz=64)University of Glasgow4 tools · gla.ac.uk](https://browser-use.com/webmcp/gla.ac.uk) - [![](https://www.google.com/s2/favicons?domain=dc.library.northwestern.edu&sz=64)Northwestern University Libraries Digital Collections2 tools · dc.library.northwestern.edu](https://browser-use.com/webmcp/dc.library.northwestern.edu) - [![](https://www.google.com/s2/favicons?domain=qu.edu&sz=64)Quinnipiac University12 tools · qu.edu](https://browser-use.com/webmcp/qu.edu) - [![](https://www.google.com/s2/favicons?domain=unej.ac.id&sz=64)Universitas Jember5 tools · unej.ac.id](https://browser-use.com/webmcp/unej.ac.id) - [![](https://www.google.com/s2/favicons?domain=querobolsa.com.br&sz=64)Quero Bolsa12 tools · querobolsa.com.br](https://browser-use.com/webmcp/querobolsa.com.br) - [![](https://www.google.com/s2/favicons?domain=addictioncenter.com&sz=64)Addiction Center2 tools · addictioncenter.com](https://browser-use.com/webmcp/addictioncenter.com) [All 738 education & health sites →](https://browser-use.com/webmcp/education-health)