{
  "fixes": {
    "slug": "atlassian-rovo-mcp",
    "name": "Atlassian Rovo MCP Server",
    "listing": "https://www.anchorterminal.com/tools/atlassian-rovo-mcp",
    "markdown": "# Fix list: Atlassian Rovo MCP Server\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/atlassian-rovo-mcp, the October 2026 research run, assessed 1 October 2026. Grade C, 58.1 out of 100.\n\nThis is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.\n\nFor a coding agent working on Atlassian Rovo MCP Server: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.\n\n## 1. Reliability, 50 out of 100, up to 10 more on the total\n\nWhy it scored 50: Statuspage at rovo.status.atlassian.com with an MCP component and an incident feed (20). One incident on that page in the last 90 days, degraded Rovo chat streaming on 18 August 2026 from 07:11 to 10:52 UTC, which doesn't name MCP, while GitHub issues 241 (11 September, every v2 tool call rejected) and 252 (22 September, us-east-1 v2 degraded) report problems the page didn't show (20). No numeric rate limits for the MCP server in the docs or the Rovo usage-limits page (0). No 429 or retry guidance found (0). We found no SLA that names the MCP server (0). v2 went GA on 8 September 2026 (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 2. Payments \u0026 pricing, 20 out of 100, up to 10 more on the total\n\nWhy it scored 20: No x402, MPP or L402 (0). Usage draws Rovo credits. The usage-limits page says single-product lookups are free and enriched Teamwork Graph calls cost 1 to 10 credits each, but no per-credit price sits next to it (10). Atlassian Cloud has free plans with no card, but we didn't confirm the MCP server is enabled on them (10). A person signs in through a browser OAuth flow or creates an API token (0).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.\n\nOpen-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.\n\n## 3. Schema \u0026 documentation, 58 out of 100, up to 6.8 more on the total\n\nWhy it scored 58: MCP tools carry JSON Schema inputs by protocol, but the server is closed and the supported-tools page lists names and one-line purposes, not schemas, so we couldn't confirm typing on every tool (15). No llms.txt, though the GitHub README is Markdown (5). Descriptions we could read are one line of purpose, such as \"Create a new Jira work item\", with no when-not-to-use (8). Inputs unverified, and issue 244 reports a getJiraIssue argument that Vertex and Gemini reject (7). The README lists troubleshooting messages and the skills give usage examples, but there's no error catalogue (8). Versioned endpoints (v1, v2) and a dated changelog with seven entries since 1 July (15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.\n\n## 4. Agent ergonomics, 63 out of 100, up to 6 more on the total\n\nWhy it scored 63: Over 200 tools in all, but v2 exposes a small set of primary tools plus discover, executeRead, executeWrite and executeDestructive, and loads the rest on demand. We couldn't count the primary set without signing in (20). Search tools take maxResults or limit, and the flat `?tools=all` list is paginated (15). Error messages are documented for IP allowlisting and auth, not per tool (10). Read, write and destructive execution are separate meta-tools, but we found no readOnlyHint or destructiveHint and no idempotency guidance (10). One URL and an OAuth sign-in, no SDK needed, required parameters per tool not published (8).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.\n\n## 5. Security \u0026 auth, 85 out of 100, up to 2.6 more on the total\n\nWhy it scored 85: OAuth 2.1 bounded by the user's existing product permissions, with scopes per permission group, or API tokens in the `Authorization` header (Basic email and token, or a service-account Bearer key), never in the URL. Personal API tokens carry the user's full reach (26). Admins grant permission groups per product, delete_jira and manage_jira are off by default, destructive calls go through their own meta-tool, and admins can block client domains and enforce IP allowlists (16). The README and SECURITY.md describe prompt injection and tool poisoning and ask for human confirmation on destructive actions, guidance only (10). Every tool call lands in the organisation audit log under Rovo MCP User Actions (15). security.txt valid per the 26 September check, a private disclosure route with a bug bounty named in SECURITY.md, and SOC 2 and ISO 27001 on the trust page, though the page doesn't say Rovo or MCP is in scope (18).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.\n\n## 6. Maintenance \u0026 community, 80 out of 100, up to 1.8 more on the total\n\nWhy it scored 80: Changelog entry on 30 September 2026 (30). Seven dated entries since 1 July, five of them in the last week of September (20). Closed service with a public changelog and a GitHub repository for feedback, where 76 issues are open and the newest ten mostly carry needs-triage with no visible reply (9). Registered as com.atlassian/atlassian-mcp-server 2.0.0 in the official MCP registry (15). The public repository holds manifests and skills with validation tests, there's no package to install (6).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## 7. Transparency \u0026 trust, 81 out of 100, up to 1.7 more on the total\n\nMade of editorial 61, provenance 100.\n\nWhy it scored 81: The hosted server is closed under Atlassian's customer agreement. The GitHub repository of docs, manifests and skills is Apache-2.0 (15). Atlassian publishes a privacy policy and DPA, but we didn't find MCP-specific retention statements and didn't fetch the DPA in this run (18). v1 retirement is dated (automatic move to v2 on 1 March 2027, /v1/sse unsupported after 30 June 2026) and tool renames are logged, with no stated notice period (18). Atlassian publishes subprocessors and data residency for Cloud, not checked for MCP in this run (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\n## Deductions\n\nEach comes off the total. A fixed and documented problem counts for less at the next check.\n\n- 2026-09-26, `findJiraIssueAssignableUsers` was renamed `listJiraIssueAssignableUsers` and the change appeared in the changelog the same day, with no advance notice, 18 days after v2 went GA. Clients pinned to flat tool names break; gateway mode rediscovers it (https://developer.atlassian.com/cloud/rovo-mcp/changelog/)\n\n## What we couldn't check\n\nWhat we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.\n\n- Numeric rate limits and 429 behaviour for mcp.atlassian.com, which no page we read states.\n- The price of a Rovo credit and whether failed calls consume credits.\n- Whether the MCP server works on Atlassian's free Cloud plans.\n- How many primary tools v2 exposes before discover, which needs a signed-in session to count.\n- Whether SOC 2 and ISO 27001 scope covers Rovo and the MCP server, and MCP-specific data retention.\n\n## Weaknesses\n\n- No numeric rate limits or 429 guidance published for the MCP server\n- Enriched Teamwork Graph calls cost 1 to 10 Rovo credits each, with no price per credit beside them\n- Tool schemas aren't published, and the supported-tools page gives one line per tool\n- 76 open GitHub issues, most of the recent ones still labelled needs-triage\n- JSM tools work only with API-token auth, and Compass only with OAuth\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Connect to `https://mcp.atlassian.com/v2/mcp`, not `/v1/sse`, which stopped being supported after 30 June 2026\n- Call `discover` before execute, since flat tool names have changed under v2\n- Pass `maxResults: 10` on JQL and CQL searches, as Atlassian's own skills require\n- Expect a permission error rather than a tool for deletes until an admin enables delete_jira\n- For headless runs send a service-account key as `Authorization: Bearer`, and note that JSM tools need this route\n\n## What the review panel asked for\n\n- Publish tool schemas\n- Move skill guidance into descriptions\n- tool annotations\n- MCP in certification scope\n\n## When it's done\n\nSend what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `\"kind\": \"dispute\"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.\n",
    "grade": "C",
    "score": 58.1,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 50,
        "maxGain": 10,
        "reason": "Statuspage at rovo.status.atlassian.com with an MCP component and an incident feed (20). One incident on that page in the last 90 days, degraded Rovo chat streaming on 18 August 2026 from 07:11 to 10:52 UTC, which doesn't name MCP, while GitHub issues 241 (11 September, every v2 tool call rejected) and 252 (22 September, us-east-1 v2 degraded) report problems the page didn't show (20). No numeric rate limits for the MCP server in the docs or the Rovo usage-limits page (0). No 429 or retry guidance found (0). We found no SLA that names the MCP server (0). v2 went GA on 8 September 2026 (10).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.",
          "Local packages, SDKs, frameworks and stdio MCP servers.",
          "- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.",
          "Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 20,
        "maxGain": 10,
        "reason": "No x402, MPP or L402 (0). Usage draws Rovo credits. The usage-limits page says single-product lookups are free and enriched Teamwork Graph calls cost 1 to 10 credits each, but no per-credit price sits next to it (10). Atlassian Cloud has free plans with no card, but we didn't confirm the MCP server is enabled on them (10). A person signs in through a browser OAuth flow or creates an API token (0).",
        "checklist": [
          "The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).",
          "- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).",
          "Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.",
          "Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 58,
        "maxGain": 6.8,
        "reason": "MCP tools carry JSON Schema inputs by protocol, but the server is closed and the supported-tools page lists names and one-line purposes, not schemas, so we couldn't confirm typing on every tool (15). No llms.txt, though the GitHub README is Markdown (5). Descriptions we could read are one line of purpose, such as \"Create a new Jira work item\", with no when-not-to-use (8). Inputs unverified, and issue 244 reports a getJiraIssue argument that Vertex and Gemini reject (7). The README lists troubleshooting messages and the skills give usage examples, but there's no error catalogue (8). Versioned endpoints (v1, v2) and a dated changelog with seven entries since 1 July (15).",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.",
          "Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 63,
        "maxGain": 6,
        "reason": "Over 200 tools in all, but v2 exposes a small set of primary tools plus discover, executeRead, executeWrite and executeDestructive, and loads the rest on demand. We couldn't count the primary set without signing in (20). Search tools take maxResults or limit, and the flat `?tools=all` list is paginated (15). Error messages are documented for IP allowlisting and auth, not per tool (10). Read, write and destructive execution are separate meta-tools, but we found no readOnlyHint or destructiveHint and no idempotency guidance (10). One URL and an OAuth sign-in, no SDK needed, required parameters per tool not published (8).",
        "checklist": [
          "- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.",
          "Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 85,
        "maxGain": 2.6,
        "reason": "OAuth 2.1 bounded by the user's existing product permissions, with scopes per permission group, or API tokens in the `Authorization` header (Basic email and token, or a service-account Bearer key), never in the URL. Personal API tokens carry the user's full reach (26). Admins grant permission groups per product, delete_jira and manage_jira are off by default, destructive calls go through their own meta-tool, and admins can block client domains and enforce IP allowlists (16). The README and SECURITY.md describe prompt injection and tool poisoning and ask for human confirmation on destructive actions, guidance only (10). Every tool call lands in the organisation audit log under Rovo MCP User Actions (15). security.txt valid per the 26 September check, a private disclosure route with a bug bounty named in SECURITY.md, and SOC 2 and ISO 27001 on the trust page, though the page doesn't say Rovo or MCP is in scope (18).",
        "checklist": [
          "- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.",
          "Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 80,
        "maxGain": 1.8,
        "reason": "Changelog entry on 30 September 2026 (30). Seven dated entries since 1 July, five of them in the last week of September (20). Closed service with a public changelog and a GitHub repository for feedback, where 76 issues are open and the newest ten mostly carry needs-triage with no visible reply (9). Registered as com.atlassian/atlassian-mcp-server 2.0.0 in the official MCP registry (15). The public repository holds manifests and skills with validation tests, there's no package to install (6).",
        "checklist": [
          "- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 81,
        "maxGain": 1.7,
        "reason": "The hosted server is closed under Atlassian's customer agreement. The GitHub repository of docs, manifests and skills is Apache-2.0 (15). Atlassian publishes a privacy policy and DPA, but we didn't find MCP-specific retention statements and didn't fetch the DPA in this run (18). v1 retirement is dated (automatic move to v2 on 1 March 2027, /v1/sse unsupported after 30 June 2026) and tool renames are logged, with no stated notice period (18). Atlassian publishes subprocessors and data residency for Cloud, not checked for MCP in this run (10).",
        "blend": "editorial 61, provenance 100",
        "checklist": [
          "- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).",
          "The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      }
    ],
    "deductions": [
      "2026-09-26, `findJiraIssueAssignableUsers` was renamed `listJiraIssueAssignableUsers` and the change appeared in the changelog the same day, with no advance notice, 18 days after v2 went GA. Clients pinned to flat tool names break; gateway mode rediscovers it (https://developer.atlassian.com/cloud/rovo-mcp/changelog/)"
    ],
    "unchecked": [
      "Numeric rate limits and 429 behaviour for mcp.atlassian.com, which no page we read states.",
      "The price of a Rovo credit and whether failed calls consume credits.",
      "Whether the MCP server works on Atlassian's free Cloud plans.",
      "How many primary tools v2 exposes before discover, which needs a signed-in session to count.",
      "Whether SOC 2 and ISO 27001 scope covers Rovo and the MCP server, and MCP-specific data retention."
    ],
    "weaknesses": [
      "No numeric rate limits or 429 guidance published for the MCP server",
      "Enriched Teamwork Graph calls cost 1 to 10 Rovo credits each, with no price per credit beside them",
      "Tool schemas aren't published, and the supported-tools page gives one line per tool",
      "76 open GitHub issues, most of the recent ones still labelled needs-triage",
      "JSM tools work only with API-token auth, and Compass only with OAuth"
    ],
    "agentNotes": [
      "Connect to `https://mcp.atlassian.com/v2/mcp`, not `/v1/sse`, which stopped being supported after 30 June 2026",
      "Call `discover` before execute, since flat tool names have changed under v2",
      "Pass `maxResults: 10` on JQL and CQL searches, as Atlassian's own skills require",
      "Expect a permission error rather than a tool for deletes until an admin enables delete_jira",
      "For headless runs send a service-account key as `Authorization: Bearer`, and note that JSM tools need this route"
    ],
    "requests": [
      {
        "text": "Publish tool schemas",
        "reviews": 1
      },
      {
        "text": "Move skill guidance into descriptions",
        "reviews": 1
      },
      {
        "text": "tool annotations",
        "reviews": 1
      },
      {
        "text": "MCP in certification scope",
        "reviews": 1
      }
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-04",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.3",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}