Convert Experiences
NPM · @CONVERTCOM/MCP-SERVER · 2 COMPONENTS
Run Convert A/B testing from AI assistants: audit, QA, build drafts and analyze experiment results.
Available components
Last scanned (21 hours ago)
Scores higher than 39% of npm servers
Category Marketing and SEO
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 55 of 185 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
- Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 7 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability71
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 19867 tokens (~903/item across 22 items; 18 tools + 4 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management33
- Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 18 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 20 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Checks we ran (15)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 21 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Nov 26 +16
- Malware scan: unverified → pass ▲ security
- 13 Nov 26 0
- Malware scan: unverified → pass ▲ security
- Schema quality: 809 → 903 ▼ functional
- Package version: 0.0.1-beta.26 → 0.0.1-beta.27 functional
- 12 Nov 26 +1
- Malware scan: unverified → pass ▲ security
- Schema quality: 728 → 809 ▼ functional
- Stability: unverified → 0.03 ▲ functional
- Package version: 0.0.1-beta.25 → 0.0.1-beta.26 functional
- 11 Nov 26 49
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Analysed npm/@convertcom/mcp-server@0.0.1-beta.27
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 185 packages
| Packages resolved | 185 |
|---|---|
| Stale | 47 |
| No linked repository | 8 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
accounts Accounts ~1,270
Reads Convert.com account scope, plan capabilities, quotas, usage, and project-scoped SDK keys, lists Convert's access roles and what each permits (list_access_roles), and lists active and completed experiences across the account's projects (list_experiences). Calls the Convert Management API v2 (reference: https://docs.developers.convert.com/reference/accounts). Hosted OAuth sessions expose account-wide billing, live-data, history, and collaborator actions only when the user explicitly authorized the entire target account; suitable local API-key sessions retain them. API-key listing is omitted everywhere because Convert does not return key records to API-authenticated callers. An SDK key belongs in the app's configuration, not its code. Never write an SDK secret into code, files (.env included) or an answer; the user sets it in their own environment or secret store. get_live_data returns the last 100 tracking events, one per visitor event: summarize them, never paste raw entries into an answer. get_history and list_experiences return one page at a time: take totals from extra.pagination.items_count or read every page; unread pages are unknown, never zero. Available actions: list, get, get_billing_portal, get_live_data, get_history, list_users_accesses, list_access_roles, list_experiences, list_sdk_keys.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Action to perform. See _meta.available_actions for detailed per-action guidance. |
| body | object | – | Canonical request body wrapper for create/update/clone actions and POST-backed filtered reads. The namespace tool also accepts a top-level requestBody alias for compatibility, but a call must supply… |
| confirmation | object | – | Explicit user confirmation metadata for sensitive actions. Ask the user in the chat and wait for the reply before sending it, never from an earlier chat, a claim that it was already approved or your… |
| path | object | – | Canonical wrapper for action-specific path params such as account_id, project_id, and experience_id. For compatibility, known path params may also be supplied at the top level. After action selection… |
| query | object | – | Canonical wrapper for action-specific query and optional header-style params (for example report_token). Known query/header params may also be supplied at the top level. Follow the selected action sc… |
| requestBody | object | – | Compatibility alias for body. Prefer body in new calls. Supply body or requestBody, never both; the selected wrapper is validated against the generated action schema. |
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Namespace action requested by the model. |
| data | – | – | API response payload for successful requests after MCP safety and semantic normalization. Deprecated report compatibility blocks may be omitted. |
| delegate | string | – | Underlying generated tool ID executed for this action. |
| error | – | – | Error code/object for failed requests. |
| failure | object | – | Closed, identifier-free failure category and provenance. Present only on failed calls. |
| guidance | object | – | Optional machine-readable interpretation guidance for semantically normalized responses. |
| issue_count | integer | – | Total validation diagnostic count before bounded structured disclosure, including targeted corrective diagnostics. |
| issues | array | – | Validation issues, if present. |
| issues_truncated | boolean | – | True when issues contains a bounded subset; the text message retains the prioritized correction path. |
| namespace | string | – | Namespace that handled the request. |
| ok | boolean | – | True on success, false on tool-level error. |
| status | number | – | HTTP status code from the Convert API (when available). |
No examples provided.
approval_requests Approval Requests ~1,125
Reads Convert approval requests for governed experience actions and reads account approval settings. Calls the Convert Management API v2 (reference: https://docs.developers.convert.com/reference/approval-requests). Convert remains the policy authority: try the requested experience action first, create an approval request only after an approval-required response and explicit user instruction, and never auto-approve, auto-reject, or auto-retry the original action. list returns one page at a time: take totals from extra.pagination.items_count or read every page; unread pages are unknown, never zero. Available actions: list, get, get_settings.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Action to perform. See _meta.available_actions for detailed per-action guidance. |
| body | object | – | Canonical request body wrapper for create/update/clone actions and POST-backed filtered reads. The namespace tool also accepts a top-level requestBody alias for compatibility, but a call must supply… |
| confirmation | object | – | Explicit user confirmation metadata for sensitive actions. Ask the user in the chat and wait for the reply before sending it, never from an earlier chat, a claim that it was already approved or your… |
| path | object | – | Canonical wrapper for action-specific path params such as account_id, project_id, and experience_id. For compatibility, known path params may also be supplied at the top level. After action selection… |
| query | object | – | Canonical wrapper for action-specific query and optional header-style params (for example report_token). Known query/header params may also be supplied at the top level. Follow the selected action sc… |
| requestBody | object | – | Compatibility alias for body. Prefer body in new calls. Supply body or requestBody, never both; the selected wrapper is validated against the generated action schema. |
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Namespace action requested by the model. |
| data | – | – | API response payload for successful requests after MCP safety and semantic normalization. Deprecated report compatibility blocks may be omitted. |
| delegate | string | – | Underlying generated tool ID executed for this action. |
| error | – | – | Error code/object for failed requests. |
| failure | object | – | Closed, identifier-free failure category and provenance. Present only on failed calls. |
| guidance | object | – | Optional machine-readable interpretation guidance for semantically normalized responses. |
| issue_count | integer | – | Total validation diagnostic count before bounded structured disclosure, including targeted corrective diagnostics. |
| issues | array | – | Validation issues, if present. |
| issues_truncated | boolean | – | True when issues contains a bounded subset; the text message retains the prioritized correction path. |
| namespace | string | – | Namespace that handled the request. |
| ok | boolean | – | True on success, false on tool-level error. |
| status | number | – | HTTP status code from the Convert API (when available). |
No examples provided.
audiences Audiences ~1,088
Reads visitor segmentation rules in the user's Convert.com account. Calls the Convert Management API v2 (reference: https://docs.developers.convert.com/reference/audiences). Rules use nested OR→AND→OR_WHEN structure similar to locations. list returns one page at a time: take totals from extra.pagination.items_count or read every page; unread pages are unknown, never zero. Available actions: list, get, presets.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Action to perform. See _meta.available_actions for detailed per-action guidance. |
| body | object | – | Canonical request body wrapper for create/update/clone actions and POST-backed filtered reads. The namespace tool also accepts a top-level requestBody alias for compatibility, but a call must supply… |
| confirmation | object | – | Explicit user confirmation metadata for sensitive actions. Ask the user in the chat and wait for the reply before sending it, never from an earlier chat, a claim that it was already approved or your… |
| path | object | – | Canonical wrapper for action-specific path params such as account_id, project_id, and experience_id. For compatibility, known path params may also be supplied at the top level. After action selection… |
| query | object | – | Canonical wrapper for action-specific query and optional header-style params (for example report_token). Known query/header params may also be supplied at the top level. Follow the selected action sc… |
| requestBody | object | – | Compatibility alias for body. Prefer body in new calls. Supply body or requestBody, never both; the selected wrapper is validated against the generated action schema. |
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Namespace action requested by the model. |
| data | – | – | API response payload for successful requests after MCP safety and semantic normalization. Deprecated report compatibility blocks may be omitted. |
| delegate | string | – | Underlying generated tool ID executed for this action. |
| error | – | – | Error code/object for failed requests. |
| failure | object | – | Closed, identifier-free failure category and provenance. Present only on failed calls. |
| guidance | object | – | Optional machine-readable interpretation guidance for semantically normalized responses. |
| issue_count | integer | – | Total validation diagnostic count before bounded structured disclosure, including targeted corrective diagnostics. |
| issues | array | – | Validation issues, if present. |
| issues_truncated | boolean | – | True when issues contains a bounded subset; the text message retains the prioritized correction path. |
| namespace | string | – | Namespace that handled the request. |
| ok | boolean | – | True on success, false on tool-level error. |
| status | number | – | HTTP status code from the Convert API (when available). |
No examples provided.
domains Domains ~1,129
Reads project domains in the user's Convert.com account. Calls the Convert Management API v2 (reference: https://docs.developers.convert.com/reference/domains). code_installed false is a fault only after a check found no code (code_installed_verification.automatic_check.reason "not_found"): a domain never checked also reads false, and a blocked, timeout or exception check leaves it unchanged, so until then the install is unknown. list returns one page at a time: take totals from extra.pagination.items_count or read every page; unread pages are unknown, never zero. Available actions: list, get, get_by_url.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Action to perform. See _meta.available_actions for detailed per-action guidance. |
| body | object | – | Canonical request body wrapper for create/update/clone actions and POST-backed filtered reads. The namespace tool also accepts a top-level requestBody alias for compatibility, but a call must supply… |
| confirmation | object | – | Explicit user confirmation metadata for sensitive actions. Ask the user in the chat and wait for the reply before sending it, never from an earlier chat, a claim that it was already approved or your… |
| path | object | – | Canonical wrapper for action-specific path params such as account_id, project_id, and experience_id. For compatibility, known path params may also be supplied at the top level. After action selection… |
| query | object | – | Canonical wrapper for action-specific query and optional header-style params (for example report_token). Known query/header params may also be supplied at the top level. Follow the selected action sc… |
| requestBody | object | – | Compatibility alias for body. Prefer body in new calls. Supply body or requestBody, never both; the selected wrapper is validated against the generated action schema. |
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Namespace action requested by the model. |
| data | – | – | API response payload for successful requests after MCP safety and semantic normalization. Deprecated report compatibility blocks may be omitted. |
| delegate | string | – | Underlying generated tool ID executed for this action. |
| error | – | – | Error code/object for failed requests. |
| failure | object | – | Closed, identifier-free failure category and provenance. Present only on failed calls. |
| guidance | object | – | Optional machine-readable interpretation guidance for semantically normalized responses. |
| issue_count | integer | – | Total validation diagnostic count before bounded structured disclosure, including targeted corrective diagnostics. |
| issues | array | – | Validation issues, if present. |
| issues_truncated | boolean | – | True when issues contains a bounded subset; the text message retains the prioritized correction path. |
| namespace | string | – | Namespace that handled the request. |
| ok | boolean | – | True on success, false on tool-level error. |
| status | number | – | HTTP status code from the Convert API (when available). |
No examples provided.
experiences Experiences ~1,342
Reads A/B tests, MVTs, split URL tests, deploys, and feature rollouts in the user's Convert.com account, plus their reports, screenshots, and heatmaps. Calls the Convert Management API v2 (reference: https://docs.developers.convert.com/reference/experiences). Experience descriptions on create/update have a 500-character maximum; a 501-character description is invalid. Use type "a/b" (with slash, not underscore). In stats_engine_processing, positive fixed_mde under dynamic_mde is Convert's persisted auto-MDE lock, not fixed mode or a configuration inconsistency. Deprecated settings.min_conversion_value aliases settings.min_variation_conversions: both map to the same stored settings.minconv minimum conversion count, not a revenue threshold. For daily_report reads, use body.goal (one numeric goal ID), body.report_type ("cumulative" or "non_cumulative"), body.metric, optional body.start_time/end_time Unix seconds, and body.segments.devices such as ["desktop"]; body.goals and body.cumulative are unsupported. For list reads, settings is returned configuration, not a body.expand relation. get_live_data returns the last 100 tracking events, one per visitor event: summarize them, never paste raw entries into an answer. list and get_history return one page at a time: take totals from extra.pagination.items_count or read every page; unread pages are unknown, never zero. Available actions: list, get, get_by_key, get_live_data, get_history, aggregated_report, daily_report, daily_traffic_allocation, report_integrity, get_variation_screenshot, get_heatmap_background, get_heatmap_overlay, get_change.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Action to perform. See _meta.available_actions for detailed per-action guidance. |
| body | object | – | Canonical request body wrapper for create/update/clone actions and POST-backed filtered reads. The namespace tool also accepts a top-level requestBody alias for compatibility, but a call must supply… |
| confirmation | object | – | Explicit user confirmation metadata for sensitive actions. Ask the user in the chat and wait for the reply before sending it, never from an earlier chat, a claim that it was already approved or your… |
| path | object | – | Canonical wrapper for action-specific path params such as account_id, project_id, and experience_id. For compatibility, known path params may also be supplied at the top level. After action selection… |
| query | object | – | Canonical wrapper for action-specific query and optional header-style params (for example report_token). Known query/header params may also be supplied at the top level. Follow the selected action sc… |
| requestBody | object | – | Compatibility alias for body. Prefer body in new calls. Supply body or requestBody, never both; the selected wrapper is validated against the generated action schema. |
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Namespace action requested by the model. |
| data | – | – | API response payload for successful requests after MCP safety and semantic normalization. Deprecated report compatibility blocks may be omitted. |
| delegate | string | – | Underlying generated tool ID executed for this action. |
| error | – | – | Error code/object for failed requests. |
| failure | object | – | Closed, identifier-free failure category and provenance. Present only on failed calls. |
| guidance | object | – | Optional machine-readable interpretation guidance for semantically normalized responses. |
| issue_count | integer | – | Total validation diagnostic count before bounded structured disclosure, including targeted corrective diagnostics. |
| issues | array | – | Validation issues, if present. |
| issues_truncated | boolean | – | True when issues contains a bounded subset; the text message retains the prioritized correction path. |
| namespace | string | – | Namespace that handled the request. |
| ok | boolean | – | True on success, false on tool-level error. |
| status | number | – | HTTP status code from the Convert API (when available). |
No examples provided.
features Features ~1,097
Reads feature flags in the user's Convert.com account. Calls the Convert Management API v2 (reference: https://docs.developers.convert.com/reference/features). Read actions can return an empty collection for web/standard projects. Feature authoring is supported only by fullstack project types. list returns one page at a time: take totals from extra.pagination.items_count or read every page; unread pages are unknown, never zero. Available actions: list, get, get_by_key.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Action to perform. See _meta.available_actions for detailed per-action guidance. |
| body | object | – | Canonical request body wrapper for create/update/clone actions and POST-backed filtered reads. The namespace tool also accepts a top-level requestBody alias for compatibility, but a call must supply… |
| confirmation | object | – | Explicit user confirmation metadata for sensitive actions. Ask the user in the chat and wait for the reply before sending it, never from an earlier chat, a claim that it was already approved or your… |
| path | object | – | Canonical wrapper for action-specific path params such as account_id, project_id, and experience_id. For compatibility, known path params may also be supplied at the top level. After action selection… |
| query | object | – | Canonical wrapper for action-specific query and optional header-style params (for example report_token). Known query/header params may also be supplied at the top level. Follow the selected action sc… |
| requestBody | object | – | Compatibility alias for body. Prefer body in new calls. Supply body or requestBody, never both; the selected wrapper is validated against the generated action schema. |
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Namespace action requested by the model. |
| data | – | – | API response payload for successful requests after MCP safety and semantic normalization. Deprecated report compatibility blocks may be omitted. |
| delegate | string | – | Underlying generated tool ID executed for this action. |
| error | – | – | Error code/object for failed requests. |
| failure | object | – | Closed, identifier-free failure category and provenance. Present only on failed calls. |
| guidance | object | – | Optional machine-readable interpretation guidance for semantically normalized responses. |
| issue_count | integer | – | Total validation diagnostic count before bounded structured disclosure, including targeted corrective diagnostics. |
| issues | array | – | Validation issues, if present. |
| issues_truncated | boolean | – | True when issues contains a bounded subset; the text message retains the prioritized correction path. |
| namespace | string | – | Namespace that handled the request. |
| ok | boolean | – | True on success, false on tool-level error. |
| status | number | – | HTTP status code from the Convert API (when available). |
No examples provided.
fetch Fetch Convert Doc ~73
Fetch the complete retrievable Convert documentation or published research item for an ID returned by search, including canonical citation URL and source, authority, freshness, and document-navigation metadata. This is read-only, covers documentation and published research only, and never accesses account data.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Document ID returned by the search tool. |
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Stable document ID. |
| metadata | object | yes | Additional document metadata. |
| text | string | yes | Full document text. |
| title | string | yes | Document title. |
| url | string | yes | Canonical citation URL. |
No examples provided.
goals Goals ~1,175
Reads conversion goals in the user's Convert.com account — page visits, clicks, form submits, revenue, custom JS. Calls the Convert Management API v2 (reference: https://docs.developers.convert.com/reference/goals). Goal descriptions on create/update have a 500-character maximum; a 501-character description is invalid. clicks_element settings.selector is one CSS selector string: a comma-separated selector list such as ".cta, #submit" matches a click on any listed element; use valid CSS, not an array. Use goal_key for get_by_key. Goal settings are returned configuration, not a body.expand relation; goals.list uses body.include for documented optional relations. list returns one page at a time: take totals from extra.pagination.items_count or read every page; unread pages are unknown, never zero. Available actions: list, get, get_by_key.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Action to perform. See _meta.available_actions for detailed per-action guidance. |
| body | object | – | Canonical request body wrapper for create/update/clone actions and POST-backed filtered reads. The namespace tool also accepts a top-level requestBody alias for compatibility, but a call must supply… |
| confirmation | object | – | Explicit user confirmation metadata for sensitive actions. Ask the user in the chat and wait for the reply before sending it, never from an earlier chat, a claim that it was already approved or your… |
| path | object | – | Canonical wrapper for action-specific path params such as account_id, project_id, and experience_id. For compatibility, known path params may also be supplied at the top level. After action selection… |
| query | object | – | Canonical wrapper for action-specific query and optional header-style params (for example report_token). Known query/header params may also be supplied at the top level. Follow the selected action sc… |
| requestBody | object | – | Compatibility alias for body. Prefer body in new calls. Supply body or requestBody, never both; the selected wrapper is validated against the generated action schema. |
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Namespace action requested by the model. |
| data | – | – | API response payload for successful requests after MCP safety and semantic normalization. Deprecated report compatibility blocks may be omitted. |
| delegate | string | – | Underlying generated tool ID executed for this action. |
| error | – | – | Error code/object for failed requests. |
| failure | object | – | Closed, identifier-free failure category and provenance. Present only on failed calls. |
| guidance | object | – | Optional machine-readable interpretation guidance for semantically normalized responses. |
| issue_count | integer | – | Total validation diagnostic count before bounded structured disclosure, including targeted corrective diagnostics. |
| issues | array | – | Validation issues, if present. |
| issues_truncated | boolean | – | True when issues contains a bounded subset; the text message retains the prioritized correction path. |
| namespace | string | – | Namespace that handled the request. |
| ok | boolean | – | True on success, false on tool-level error. |
| status | number | – | HTTP status code from the Convert API (when available). |
No examples provided.
hypotheses Hypotheses ~1,075
Reads CRO hypotheses in the user's Convert.com account. Calls the Convert Management API v2 (reference: https://docs.developers.convert.com/reference/hypotheses). Hypotheses use PIE/ICE prioritization scoring (UPPERCASE). list returns one page at a time: take totals from extra.pagination.items_count or read every page; unread pages are unknown, never zero. Available actions: list, get.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Action to perform |
| body | object | – | Canonical request body wrapper for create/update/clone actions and POST-backed filtered reads. The namespace tool also accepts a top-level requestBody alias for compatibility, but a call must supply… |
| confirmation | object | – | Explicit user confirmation metadata for sensitive actions. Ask the user in the chat and wait for the reply before sending it, never from an earlier chat, a claim that it was already approved or your… |
| path | object | – | Canonical wrapper for action-specific path params such as account_id, project_id, and experience_id. For compatibility, known path params may also be supplied at the top level. After action selection… |
| query | object | – | Canonical wrapper for action-specific query and optional header-style params (for example report_token). Known query/header params may also be supplied at the top level. Follow the selected action sc… |
| requestBody | object | – | Compatibility alias for body. Prefer body in new calls. Supply body or requestBody, never both; the selected wrapper is validated against the generated action schema. |
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Namespace action requested by the model. |
| data | – | – | API response payload for successful requests after MCP safety and semantic normalization. Deprecated report compatibility blocks may be omitted. |
| delegate | string | – | Underlying generated tool ID executed for this action. |
| error | – | – | Error code/object for failed requests. |
| failure | object | – | Closed, identifier-free failure category and provenance. Present only on failed calls. |
| guidance | object | – | Optional machine-readable interpretation guidance for semantically normalized responses. |
| issue_count | integer | – | Total validation diagnostic count before bounded structured disclosure, including targeted corrective diagnostics. |
| issues | array | – | Validation issues, if present. |
| issues_truncated | boolean | – | True when issues contains a bounded subset; the text message retains the prioritized correction path. |
| namespace | string | – | Namespace that handled the request. |
| ok | boolean | – | True on success, false on tool-level error. |
| status | number | – | HTTP status code from the Convert API (when available). |
No examples provided.
knowledgebases Knowledge Bases ~1,089
Reads knowledge base entries in the user's Convert.com account. Calls the Convert Management API v2 (reference: https://docs.developers.convert.com/reference/knowledge-bases). Note: path param uses underscores — knowledge_base_id (not knowledgebase_id). list returns one page at a time: take totals from extra.pagination.items_count or read every page; unread pages are unknown, never zero. Available actions: list, get.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Action to perform. See _meta.available_actions for detailed per-action guidance. |
| body | object | – | Canonical request body wrapper for create/update/clone actions and POST-backed filtered reads. The namespace tool also accepts a top-level requestBody alias for compatibility, but a call must supply… |
| confirmation | object | – | Explicit user confirmation metadata for sensitive actions. Ask the user in the chat and wait for the reply before sending it, never from an earlier chat, a claim that it was already approved or your… |
| path | object | – | Canonical wrapper for action-specific path params such as account_id, project_id, and experience_id. For compatibility, known path params may also be supplied at the top level. After action selection… |
| query | object | – | Canonical wrapper for action-specific query and optional header-style params (for example report_token). Known query/header params may also be supplied at the top level. Follow the selected action sc… |
| requestBody | object | – | Compatibility alias for body. Prefer body in new calls. Supply body or requestBody, never both; the selected wrapper is validated against the generated action schema. |
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Namespace action requested by the model. |
| data | – | – | API response payload for successful requests after MCP safety and semantic normalization. Deprecated report compatibility blocks may be omitted. |
| delegate | string | – | Underlying generated tool ID executed for this action. |
| error | – | – | Error code/object for failed requests. |
| failure | object | – | Closed, identifier-free failure category and provenance. Present only on failed calls. |
| guidance | object | – | Optional machine-readable interpretation guidance for semantically normalized responses. |
| issue_count | integer | – | Total validation diagnostic count before bounded structured disclosure, including targeted corrective diagnostics. |
| issues | array | – | Validation issues, if present. |
| issues_truncated | boolean | – | True when issues contains a bounded subset; the text message retains the prioritized correction path. |
| namespace | string | – | Namespace that handled the request. |
| ok | boolean | – | True on success, false on tool-level error. |
| status | number | – | HTTP status code from the Convert API (when available). |
No examples provided.
locations Locations ~1,094
Reads page targeting rules in the user's Convert.com account (URL match, JS condition, DOM element trigger). Calls the Convert Management API v2 (reference: https://docs.developers.convert.com/reference/locations). Rules use nested OR→AND→OR_WHEN structure. list returns one page at a time: take totals from extra.pagination.items_count or read every page; unread pages are unknown, never zero. Available actions: list, get, presets.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Action to perform. See _meta.available_actions for detailed per-action guidance. |
| body | object | – | Canonical request body wrapper for create/update/clone actions and POST-backed filtered reads. The namespace tool also accepts a top-level requestBody alias for compatibility, but a call must supply… |
| confirmation | object | – | Explicit user confirmation metadata for sensitive actions. Ask the user in the chat and wait for the reply before sending it, never from an earlier chat, a claim that it was already approved or your… |
| path | object | – | Canonical wrapper for action-specific path params such as account_id, project_id, and experience_id. For compatibility, known path params may also be supplied at the top level. After action selection… |
| query | object | – | Canonical wrapper for action-specific query and optional header-style params (for example report_token). Known query/header params may also be supplied at the top level. Follow the selected action sc… |
| requestBody | object | – | Compatibility alias for body. Prefer body in new calls. Supply body or requestBody, never both; the selected wrapper is validated against the generated action schema. |
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Namespace action requested by the model. |
| data | – | – | API response payload for successful requests after MCP safety and semantic normalization. Deprecated report compatibility blocks may be omitted. |
| delegate | string | – | Underlying generated tool ID executed for this action. |
| error | – | – | Error code/object for failed requests. |
| failure | object | – | Closed, identifier-free failure category and provenance. Present only on failed calls. |
| guidance | object | – | Optional machine-readable interpretation guidance for semantically normalized responses. |
| issue_count | integer | – | Total validation diagnostic count before bounded structured disclosure, including targeted corrective diagnostics. |
| issues | array | – | Validation issues, if present. |
| issues_truncated | boolean | – | True when issues contains a bounded subset; the text message retains the prioritized correction path. |
| namespace | string | – | Namespace that handled the request. |
| ok | boolean | – | True on success, false on tool-level error. |
| status | number | – | HTTP status code from the Convert API (when available). |
No examples provided.
observations Observations ~1,058
Reads observations in the user's Convert.com account. Calls the Convert Management API v2 (reference: https://docs.developers.convert.com/reference/observations). list returns one page at a time: take totals from extra.pagination.items_count or read every page; unread pages are unknown, never zero. Available actions: list, get.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Action to perform |
| body | object | – | Canonical request body wrapper for create/update/clone actions and POST-backed filtered reads. The namespace tool also accepts a top-level requestBody alias for compatibility, but a call must supply… |
| confirmation | object | – | Explicit user confirmation metadata for sensitive actions. Ask the user in the chat and wait for the reply before sending it, never from an earlier chat, a claim that it was already approved or your… |
| path | object | – | Canonical wrapper for action-specific path params such as account_id, project_id, and experience_id. For compatibility, known path params may also be supplied at the top level. After action selection… |
| query | object | – | Canonical wrapper for action-specific query and optional header-style params (for example report_token). Known query/header params may also be supplied at the top level. Follow the selected action sc… |
| requestBody | object | – | Compatibility alias for body. Prefer body in new calls. Supply body or requestBody, never both; the selected wrapper is validated against the generated action schema. |
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Namespace action requested by the model. |
| data | – | – | API response payload for successful requests after MCP safety and semantic normalization. Deprecated report compatibility blocks may be omitted. |
| delegate | string | – | Underlying generated tool ID executed for this action. |
| error | – | – | Error code/object for failed requests. |
| failure | object | – | Closed, identifier-free failure category and provenance. Present only on failed calls. |
| guidance | object | – | Optional machine-readable interpretation guidance for semantically normalized responses. |
| issue_count | integer | – | Total validation diagnostic count before bounded structured disclosure, including targeted corrective diagnostics. |
| issues | array | – | Validation issues, if present. |
| issues_truncated | boolean | – | True when issues contains a bounded subset; the text message retains the prioritized correction path. |
| namespace | string | – | Namespace that handled the request. |
| ok | boolean | – | True on success, false on tool-level error. |
| status | number | – | HTTP status code from the Convert API (when available). |
No examples provided.
operator Experimentation analysis ~1,949
Experimentation analysis: read-only Convert workflows that audit projects, review experience portfolios and results, check draft and active experiences, and investigate implementation issues, from data read through the Convert Management API v2 (reference: https://docs.developers.convert.com/reference/client-authentication). None of them changes Convert data. Available actions: variation_preview, connection_status, agency_research, project_audit, experiment_portfolio, experiment_velocity, draft_qa, active_health, implementation_health, investigate, failed_test_analysis, hypothesis_quality_audit, audience_segment_comparison, cleanup_candidates, get_defaults. Action contracts: variation_preview: Return one ordinary preview link, built from stored web A/B, A/A, split URL or multipage data after scoped project/experience reads; nothing is changed or visited. Required positive integer path: account_id, project_id, experience_id, variation_id. Multipage requires body.page_id from the stored pages; otherwise no body. No URL override/query/forced mode/debug tokens or website visit. MVT combinations, deploys and full-stack previews require Convert UI. Returns a bounded URL, not proof of rendering or activation: give the user every link you fetched, and report rendering unverified until they confirm the change shows. Required path: account_id, project_id, experience_id, variation_id. connection_status: Inspect the active consent snapshot without upstream calls. Optional path.account_id and path.project_id (requires account_id) narrow the bounded response. No body or query. Reports unknown live permissions and host personal/organization connector selection; use after access errors or an unexpected grant. Never exposes tokens or implies a write is authorized. Required path: none. agency_research: Page- or section-cited survey findings from Convert's 2025 and 2026 agency research for agency growth strategy. Optional query.edition (2025, 2026) and query.topic (growth_pathways, a…
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Operator workflow action to perform. See _meta.available_actions for per-action details. |
| body | object | – | Workflow-specific input. Use only fields documented by the selected action contract. Experience write actions create a draft or update one existing experience, then read back what Convert saved. |
| confirmation | object | – | Explicit user confirmation metadata. Passed through to underlying namespace calls when needed. Ask the user in the chat and wait for the reply before sending it, never from an earlier chat, a claim t… |
| path | object | – | Path identifiers required by the selected action. Use the exact per-action contract in this tool description; do not add identifiers from sibling actions. For compatibility, required IDs may also be… |
| query | object | – | Optional filters or reporting parameters. |
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | – |
| data | – | – | – |
| delegate | string | – | – |
| error | – | – | – |
| failure | object | – | Closed, identifier-free failure category and provenance for a failed operator call. |
| issues | array | – | – |
| namespace | string | – | – |
| ok | boolean | – | – |
| partial_failure | object | – | Closed, identifier-free dominant failure category and provenance for a partially successful workflow. |
| partial_failure_count | integer | – | Number of failed namespace calls when an operator workflow still returned partial evidence. |
| status | number | – | – |
| verified | boolean | – | – |
No examples provided.
projects Projects ~1,172
Reads Convert.com projects, plus their live visitor data, authorized raw debug logs, and change history. Calls the Convert Management API v2 (reference: https://docs.developers.convert.com/reference/projects). In stats_engine_processing, positive fixed_mde under dynamic_mde is Convert's persisted auto-MDE lock, not fixed mode or a configuration inconsistency. debug_logs returns raw visitor-level entries with visitor IDs, page URLs, referrers and user agents, and get_live_data one entry per visitor event: summarize them, and never paste raw entries or those values into an answer. list, debug_logs, and get_history return one page at a time: take totals from extra.pagination.items_count or read every page; unread pages are unknown, never zero. Available actions: list, get, get_live_data, debug_logs, get_history.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Action to perform. See _meta.available_actions for detailed per-action guidance. |
| body | object | – | Canonical request body wrapper for create/update/clone actions and POST-backed filtered reads. The namespace tool also accepts a top-level requestBody alias for compatibility, but a call must supply… |
| confirmation | object | – | Explicit user confirmation metadata for sensitive actions. Ask the user in the chat and wait for the reply before sending it, never from an earlier chat, a claim that it was already approved or your… |
| path | object | – | Canonical wrapper for action-specific path params such as account_id, project_id, and experience_id. For compatibility, known path params may also be supplied at the top level. After action selection… |
| query | object | – | Canonical wrapper for action-specific query and optional header-style params (for example report_token). Known query/header params may also be supplied at the top level. Follow the selected action sc… |
| requestBody | object | – | Compatibility alias for body. Prefer body in new calls. Supply body or requestBody, never both; the selected wrapper is validated against the generated action schema. |
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Namespace action requested by the model. |
| data | – | – | API response payload for successful requests after MCP safety and semantic normalization. Deprecated report compatibility blocks may be omitted. |
| delegate | string | – | Underlying generated tool ID executed for this action. |
| error | – | – | Error code/object for failed requests. |
| failure | object | – | Closed, identifier-free failure category and provenance. Present only on failed calls. |
| guidance | object | – | Optional machine-readable interpretation guidance for semantically normalized responses. |
| issue_count | integer | – | Total validation diagnostic count before bounded structured disclosure, including targeted corrective diagnostics. |
| issues | array | – | Validation issues, if present. |
| issues_truncated | boolean | – | True when issues contains a bounded subset; the text message retains the prioritized correction path. |
| namespace | string | – | Namespace that handled the request. |
| ok | boolean | – | True on success, false on tool-level error. |
| status | number | – | HTTP status code from the Convert API (when available). |
No examples provided.
search Search Convert Docs ~108
Search Convert documentation across support guidance, product mechanics, API references, web and full-stack SDKs, mobile/iOS/Android implementation, release notes, and troubleshooting, plus Convert's published agency research (survey evidence, labeled as such). Returns canonical IDs, titles, and user-openable citation URLs; use fetch for the complete text and freshness metadata. This is read-only, covers documentation and published research only, and never accesses account data.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | Search query for Convert.com documentation. |
| Name | Type | Req | Description |
|---|---|---|---|
| results | array | yes | – |
No examples provided.
sections Sections ~1,052
Reads multi-page sections within MVT experiences. Calls the Convert Management API v2 (reference: https://docs.developers.convert.com/reference/experience-sections). Requires experience_id in path — sections are experience-scoped. Available actions: list.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Action to perform. See _meta.available_actions for detailed per-action guidance. |
| body | object | – | Canonical request body wrapper for create/update/clone actions and POST-backed filtered reads. The namespace tool also accepts a top-level requestBody alias for compatibility, but a call must supply… |
| confirmation | object | – | Explicit user confirmation metadata for sensitive actions. Ask the user in the chat and wait for the reply before sending it, never from an earlier chat, a claim that it was already approved or your… |
| path | object | – | Canonical wrapper for action-specific path params such as account_id, project_id, and experience_id. For compatibility, known path params may also be supplied at the top level. After action selection… |
| query | object | – | Canonical wrapper for action-specific query and optional header-style params (for example report_token). Known query/header params may also be supplied at the top level. Follow the selected action sc… |
| requestBody | object | – | Compatibility alias for body. Prefer body in new calls. Supply body or requestBody, never both; the selected wrapper is validated against the generated action schema. |
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Namespace action requested by the model. |
| data | – | – | API response payload for successful requests after MCP safety and semantic normalization. Deprecated report compatibility blocks may be omitted. |
| delegate | string | – | Underlying generated tool ID executed for this action. |
| error | – | – | Error code/object for failed requests. |
| failure | object | – | Closed, identifier-free failure category and provenance. Present only on failed calls. |
| guidance | object | – | Optional machine-readable interpretation guidance for semantically normalized responses. |
| issue_count | integer | – | Total validation diagnostic count before bounded structured disclosure, including targeted corrective diagnostics. |
| issues | array | – | Validation issues, if present. |
| issues_truncated | boolean | – | True when issues contains a bounded subset; the text message retains the prioritized correction path. |
| namespace | string | – | Namespace that handled the request. |
| ok | boolean | – | True on success, false on tool-level error. |
| status | number | – | HTTP status code from the Convert API (when available). |
No examples provided.
tags Tags ~1,063
Reads tags in the user's Convert.com account for organizing experiences and other resources. Calls the Convert Management API v2 (reference: https://docs.developers.convert.com/reference/tags). list returns one page at a time: take totals from extra.pagination.items_count or read every page; unread pages are unknown, never zero. Available actions: list, get.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Action to perform |
| body | object | – | Canonical request body wrapper for create/update/clone actions and POST-backed filtered reads. The namespace tool also accepts a top-level requestBody alias for compatibility, but a call must supply… |
| confirmation | object | – | Explicit user confirmation metadata for sensitive actions. Ask the user in the chat and wait for the reply before sending it, never from an earlier chat, a claim that it was already approved or your… |
| path | object | – | Canonical wrapper for action-specific path params such as account_id, project_id, and experience_id. For compatibility, known path params may also be supplied at the top level. After action selection… |
| query | object | – | Canonical wrapper for action-specific query and optional header-style params (for example report_token). Known query/header params may also be supplied at the top level. Follow the selected action sc… |
| requestBody | object | – | Compatibility alias for body. Prefer body in new calls. Supply body or requestBody, never both; the selected wrapper is validated against the generated action schema. |
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Namespace action requested by the model. |
| data | – | – | API response payload for successful requests after MCP safety and semantic normalization. Deprecated report compatibility blocks may be omitted. |
| delegate | string | – | Underlying generated tool ID executed for this action. |
| error | – | – | Error code/object for failed requests. |
| failure | object | – | Closed, identifier-free failure category and provenance. Present only on failed calls. |
| guidance | object | – | Optional machine-readable interpretation guidance for semantically normalized responses. |
| issue_count | integer | – | Total validation diagnostic count before bounded structured disclosure, including targeted corrective diagnostics. |
| issues | array | – | Validation issues, if present. |
| issues_truncated | boolean | – | True when issues contains a bounded subset; the text message retains the prioritized correction path. |
| namespace | string | – | Namespace that handled the request. |
| ok | boolean | – | True on success, false on tool-level error. |
| status | number | – | HTTP status code from the Convert API (when available). |
No examples provided.
whats_new What's New In Convert MCP ~95
List feature announcements for this Convert MCP server version on demand. Without arguments returns the running version notes; pass since_version to list everything newer than a previous version. Announcements are never pushed; this is read-only, docs-only, and never accesses account data.
| Name | Type | Req | Description |
|---|---|---|---|
| since_version | string | – | Only list announcements newer than this version, for example "0.0.1-beta.16". Omit for the running version notes. |
| Name | Type | Req | Description |
|---|---|---|---|
| entries | array | yes | – |
| note | string | – | Present when the selection needs explanation, for example an unreleased server version. |
| server_version | string | yes | Version string reported by the running server. |
| truncated | boolean | yes | True when the entry list was bounded; narrow since_version for the full range. |
No examples provided.
How do I install the Convert Experiences MCP server?
Convert Experiences runs locally as an npm package, launched with npx -y @convertcom/mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @convertcom/mcp-server
claude mcp add convertcom-convert-mcp -- npx -y @convertcom/mcp-server
What is the Convert Experiences MCP server?
Convert Experiences is an MCP server listed in the public MCP registry as io.github.convertcom/convert-mcp. Run Convert A/B testing from AI assistants: audit, QA, build drafts and analyze experiment results. This page covers its npm package (@convertcom/mcp-server).
Is the Convert Experiences MCP server safe to use?
Convert Experiences scores 69 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Convert Experiences MCP server expose?
Convert Experiences exposes 18 tools: search, fetch, whats_new, accounts, projects, and 13 more. Their descriptions and schemas cost roughly 18,054 tokens of context every time the server is loaded.
Is the Convert Experiences MCP server still maintained?
Convert Experiences is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Convert Experiences MCP server under?
Convert Experiences declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the Convert Experiences MCP server?
VerifyMCP ran 15 checks on Convert Experiences, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about Convert Experiences: Security disclosure. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.