# PlanetScale MCP Server > PlanetScale's hosted MCP server connects agents to PlanetScale Postgres, Vitess and Neki databases. Its 25 tools cover organisations, branches, schema, read and write SQL, Insights data, Postgres logs, invoices and documentation search, with OAuth or a service token. - Canonical: https://www.anchorterminal.com/tools/planetscale-mcp - Markdown: https://www.anchorterminal.com/tools/planetscale-mcp.md (~8,450 tokens) - Slim: https://www.anchorterminal.com/tools/planetscale-mcp.min.md (~1,880 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/planetscale-mcp.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - Updated: 2026-10-10 ## Overview **Grade B · 66.4/100 · rank #292 of 950 · #5 in Databases & files · not agent-ready · confidence medium** ## Assessment OAuth scopes set no, read-only or full database access per organisation or database, each query runs on a credential created and deleted for that call, and an insights-only endpoint drops both SQL tools. Destructive statements are gated by a flag the model sets itself, no rate limit was found, and every plan needs a card. ## Facts | Field | Value | | --- | --- | | Vendor | PlanetScale (https://planetscale.com) | | Kind | MCP server | | Category | Databases & files (https://www.anchorterminal.com/categories/data) | | Transport | Streamable HTTP | | Endpoint | `https://mcp.pscale.dev/mcp/planetscale` | | Auth | OAuth or key · OAuth by default. Each MCP client registers as an OAuth application and the person signs in and chooses no, read-only or full access per organisation or per database, with payment-method access set separately. For CI and headless clients a service token secret (`pscale_tkn_`) goes in an `Authorization: Bearer` header, with permissions granted on the token in organisation settings. Claude.ai, Claude for desktop, Claude Managed Agents and Notion accept OAuth only. Access is self-serve after a person signs up. | | Pricing | Paid ($5 / mo) · No charge for the MCP server was found beyond the database plan, and a PlanetScale database is needed for most tools. No free tier or trial was found, and all plans need a payment method on file. Clusters are priced by month, from $5 for a single-node Postgres PS-5 in AWS us-east-1, with storage, backups and egress billed separately (https://planetscale.com/pricing.md, checked 2026-10-09). | | x402 | No · No x402, MPP or L402 in the MCP docs, the pricing page or the tool source (checked 2026-10-09). | | Licence | Proprietary hosted service under PlanetScale's Terms of Service. The 13 tools in planetscale/mcp-server are Apache-2.0 | | Tools exposed | 25 | | MCP registry name | `io.github.planetscale/mcp-server` | | Source | https://github.com/planetscale/mcp-server | | Docs | https://planetscale.com/docs/mcp-server | | llms.txt | https://planetscale.com/docs/llms.txt | | Last release | 2026-10-08 | | Endpoints | https://mcp.pscale.dev/mcp/planetscale (all 25 tools) and https://mcp.pscale.dev/mcp/planetscale-insights-only (no SQL tools). Streamable HTTP | | Tools | 25. Organisations, databases and branches (list and get), branch schema, read query, write query, Insights, schema recommendations, query error patterns and executions, query tags and summaries, Postgres logs, regions, cluster sizes, invoices and line items, payment method (show, update, setup status), documentation search | | Databases | PlanetScale Postgres, Vitess (MySQL) and Neki (sharded Postgres, in platform preview since 10 September 2026) | | Credentials | OAuth with per-client registration and scopes of no, read-only or full access per organisation or database, plus a separate payment-method scope. Service tokens (`pscale_tkn_`) as a Bearer header for CI and headless clients, with per-permission grants | | Query safeguards | Per-call database credentials deleted after use. Reads go to a replica by default. TRUNCATE and unfiltered UPDATE or DELETE blocked. DELETE and DDL need `confirm_destructive`. 50-second limit. Queries tagged `source=planetscale-mcp` | | Rate limits | None found for the MCP server or the API. The OpenAPI file lists a 429 response with no figures | | Output limits | Insights 5 results a metric by default, 20 at most. Error, tag and log tools take `limit` and report `truncated` or `has_next`. Query tools return all rows | | Source | github.com/planetscale/mcp-server, Apache-2.0, 13 of the 25 tools, built on `@gram-ai/functions`. Package version 0.0.0, no tags, 100 commits from 24 January to 17 September 2026 | | Registry | `io.github.planetscale/mcp-server` 1.0.0 in the official MCP registry, published 15 April 2026. Also in the Claude connectors directory and as a Claude Code plugin, per the docs | | Free tier | None found. All plans need a payment method on file | | Prices | AWS us-east-1. Postgres single node from $5 a month (PS-5), Postgres with two replicas from $15, Vitess from $39 (PS-10), Neki from $30 a shard. Storage, backups and egress are billed separately | | SLA | 99.99 per cent for single-region and 99.999 per cent for multi-region clusters, service credits of 10 to 50 per cent. Single-node clusters and beta functions excluded (updated 27 August 2026) | | Status | planetscalestatus.com on incident.io, components by engine, cloud and region, plus Database Operations, Dashboard and API Requests, and Query Insights | | Certifications | SOC 1 Type 2 and SOC 2 Type 2 with HIPAA on all plans, PCI DSS 4.0.1 Level 1 for PlanetScale Managed, reports through trust.planetscale.com (not read) | | Audit | Organisation audit log and security log on all plans. Installed OAuth apps can be reviewed and revoked since 28 September 2026 | | Capabilities | db.sql, db.admin | | Tags | official, hosted, mcp, oauth, read-only-mode, paid, postgres, mysql, llms-txt, openapi, status-page, soc2, database | | JSON | https://www.anchorterminal.com/api/v1/tools/planetscale-mcp.json | ## Score breakdown (methodology v0.4, October 2026 research run) Assessed 2026-10-09 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 63 | 12.6 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 82 | 13.3 | | Agent ergonomics | 13% | 16.2 | 74 | 12.0 | | Security & auth | 14% | 17.5 | 77 | 13.5 | | Payments & pricing | 10% | 12.5 | 15 | 1.9 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 80 | 7.0 | | Transparency & trust (editorial 66, provenance 73) | 7% | 8.8 | 70 | 6.1 | | Negative events | up to −15 | up to −15 | none recorded | 0 | | **Total** | | | | **66.4 → B** | ### Why each score - Reliability 63: Graded as a hosted service. Status page at planetscalestatus.com with per-region component uptime for July to October 2026 (20). The page shows no open incident and its lowest figures are 99.71 per cent for Query Insights, 99.97 per cent for Postgres in us-east-1 and 99.98 per cent for Dashboard and API Requests. The incident entries are script-drawn and went unread, so the record is scored from the uptime figures as minor only (20). No rate limit with numbers was found for the MCP server or the API (0). The OpenAPI file lists a 429 response that says to reduce request frequency, with no Retry-After or backoff guidance, and no idempotency key for writes. The 50-second query limit is documented (3). The SLA commits to 99.99 per cent for single-region and 99.999 per cent for multi-region clusters with service credits, and excludes single-node clusters and beta functions (10). The docs give the MCP server no beta or preview label and the registry entry is 1.0.0 (10). Total 63. - Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes. - Schema & documentation 82: The 13 tools in planetscale/mcp-server have typed zod input schemas, and the other 12 are generated from the public OpenAPI file at planetscale.com/docs/openapi.yaml, 304 operations (25). llms.txt and a Markdown twin of every docs page (10). The custom descriptions state purpose, limits and when to ask the person, for example the 50-second limit, row-level security on Postgres reads and the Checkout sequence for the payment tools. The generated tools are one-line summaries (17). Enums for log levels and summary fields, clamped limits and required fields. `organization`, `database` and `branch` are free strings and SQL is free text by nature (12). The docs give example prompts and a permissions table per tool. Tool errors are plain text beginning `Error:` with the API status code (10). The product changelog is dated and carries MCP entries, but the server has no version history of its own. The package is 0.0.0, the repository has no tags or changelog, and the registry entry has stayed at 1.0.0 since 15 April 2026 (8). Total 82. The tool definitions were read from the source and the docs, not from the live server, which answers 401 without a token. - Agent ergonomics 74: 25 tools (15). The insights-only endpoint drops the two SQL tools, and OAuth scopes limit which tool groups a client is granted (5). Insights, error, tag and log tools take `limit` with documented maxima and report `truncated` or `has_next`, and the logs tool pages. `planetscale_execute_read_query` returns every row with no cap (15). Error texts say what to do next, for example the safe-migrations message with two ways forward, the `postgres_rls_active` warning on empty results and the full-access message on a payment 403 (15). The 13 source tools set `readOnlyHint` and `destructiveHint`, with a test that fails on a missing annotation. Annotations on the 12 generated tools were not read. No idempotency for writes was found, though the payment tool tells the model not to start a second setup while one is pending (15). Sensible defaults (replica routing, 24-hour windows, curated metrics), but three identifiers are required on nearly every call. Official SDKs do not apply to a hosted MCP server and none were checked (9). Total 74. - Security & auth 77: OAuth with each client registered as an OAuth application, scopes that set no, read-only or full access per organisation or per database, a separate payment-method scope, and service tokens with per-permission grants for headless use. Each query runs on a database credential created for the call and deleted after it (30). Read queries use a reader password on Vitess and a `pg_read_all_data` role on Postgres that does not bypass row-level security. An insights-only endpoint has no SQL tools, and since 8 October 2026 administrators can cap members' grants at none, read-only or read and write. TRUNCATE and UPDATE or DELETE without WHERE are blocked. DELETE and DDL need `confirm_destructive`, which the model sets itself, and the check is a regular expression on the start of the statement. Write queries run as the `postgres` role or a Vitess admin password. Read and write is the default (16). Query results return database content to the model. The docs warn about write access to production, and no prompt-injection guidance or result wrapping was found (4). Organisation audit log and security log on all plans, every MCP query tagged `source=planetscale-mcp` in Insights, and a list of installed OAuth apps with revoke (13). Vulnerability disclosure policy with security@planetscale.com, SOC 1 Type 2 and SOC 2 Type 2 with HIPAA, PCI DSS for PlanetScale Managed. security.txt returns 404 and no bug bounty was found (14). Total 77. - Payments & pricing 15: No x402, MPP or L402 in the MCP docs, the pricing page or the source (0). Monthly prices for every cluster size are public without a login, as a Markdown page and as a read-only SQL catalogue, from $5 a month for a single-node Postgres PS-5. Storage, backup and egress rates were not on the page read, and there is no per-call price (15). No free tier or trial was found, and the billing docs say all plans need a valid payment method on file (0). A person signs up in a browser and authorises OAuth or creates a service token in organisation settings (0). Total 15. - Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored. - Maintenance & community 80: The changelog's newest MCP entry is 8 October 2026 (organisation MCP query access), and the repository's last commit is 17 September 2026 (30). Commits on 13 days since 11 July added Postgres logs, query errors, query tags, payment tools, annotations and Neki support, and the changelog has MCP or OAuth entries on 28 September and 8 October (20). Closed hosted service with a dated public changelog, a support desk and a Discord community. The repository's issues and pull requests were not read (10). Listed in the official MCP registry as `io.github.planetscale/mcp-server`, a GitHub-verified namespace, version 1.0.0 published 15 April 2026 (15). Dependencies are current (`@modelcontextprotocol/sdk` ^1.30, zod 4) and the repository has unit tests, but no CI workflow is published (5). Total 80. - Transparency & trust 70: The tools PlanetScale maintains by hand are public under Apache-2.0. The hosted server, its OAuth layer and the 12 generated tools are closed, under the Terms of Service of 25 August 2026 (22). Privacy Policy of 23 July 2026, a DPA covering all plans and a data-locality statement in the security docs. Retention is described without periods, and the DPA was not read (20). The Terms of Service promise at least six months' notice before material functionality is discontinued, with exceptions. The docs say the local `pscale mcp` server has been removed, with no date (14). Customers choose the cloud region and the security docs refer to sub-processors, but the list was not read. The MCP endpoint's response headers name Gram, Speakeasy's hosting platform, and no page read says how tool calls are handled there (10). Total 66. Fix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (26 items): https://www.anchorterminal.com/fixes/planetscale-mcp.md (JSON https://www.anchorterminal.com/fixes/planetscale-mcp.json) ### What we couldn't check - unchecked: the tool definitions as the live server serves them. `initialize` answered 401 without a token, so `tools/list` was not sent. The 13 source tools were read from the repository and the 12 generated ones from the docs list and the OpenAPI file - unchecked: annotations and input schemas of the 12 generated tools as served - unchecked: rate limits. None in the MCP docs, the service-token page or the OpenAPI file. The API reference pages were not read, to keep to the page budget for planetscale.com - unchecked: incident entries on planetscalestatus.com, which are script-drawn. The reliability record rests on the component uptime figures for July to October 2026 - unchecked: the DPA, the acceptable use policy, the sub-processor list and trust.planetscale.com - unchecked: the audit log docs page. The audit and security logs are taken from the plan table on the security page - unchecked: open issues and pull requests on planetscale/mcp-server, and its star count - unchecked: storage, backup and egress rates, which were not on the pricing page read - Whether Speakeasy, whose Gram platform serves the endpoint per the response headers, is a named sub-processor, and whether tool inputs and results are logged there - When the local `pscale mcp` server was removed and whether users were given notice - Whether the hosted server shows the DDL and DELETE confirmation to the person through the client. In the source it is a flag the model sets - The weakness about the write-query check comes from reading the regular expressions in the source. It was not tested against the service - PlanetScale's Website Terms of Service (27 December 2021) forbid any robot, spider or automatic process retrieving the site. robots.txt allows every path and says ai-input=yes. No deduction, and it matters before any probe is run - 17 requests went to planetscale.com, two over the brief's fifteen, to read the Terms of Service and the OpenAPI file - The lead was right about the endpoint, the 25 tools, OAuth and service tokens, and the removal of the local server ### Sources - MCP server docs (Markdown twin): (seen 2026-10-09) - MCP service token docs: (seen 2026-10-09) - MCP server tool source, cloned at commit 2911c85 of 17 September 2026: (seen 2026-10-09) - write-query validator source: (seen 2026-10-09) - docs index for agents: (seen 2026-10-09) - OpenAPI file, read as the description file and not the rendered API reference: (seen 2026-10-09) - pricing (Markdown twin): (seen 2026-10-09) - billing docs: (seen 2026-10-09) - changelog: (seen 2026-10-09) - security and compliance docs: (seen 2026-10-09) - vulnerability disclosure policy: (seen 2026-10-09) - Terms of Service, last updated 25 August 2026: (seen 2026-10-09) - Website Terms of Service, last updated 27 December 2021: (seen 2026-10-09) - Privacy Policy, last updated 23 July 2026: (seen 2026-10-09) - Service Level Agreement, last updated 27 August 2026: (seen 2026-10-09) - status page: (seen 2026-10-09) - official MCP registry search: (seen 2026-10-09) - hosted endpoint, one unauthenticated `initialize` (401): (seen 2026-10-09) - robots.txt (allows all, ai-input=yes) and security.txt (404): (seen 2026-10-09) - RDAP record for planetscale.com: (seen 2026-10-09) ## Who's behind it (provenance 73/100, checked 2026-10-09) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | PlanetScale, Inc. | 20/20 | | Domain age | planetscale.com, registered 2011-10-06 (15 years) | 15/15 | | Endpoint on the vendor's domain | mcp.pscale.dev is not on planetscale.com | 0/15 | | Terms of service | read, states 6 of the 7 things a reader expects | 9.1/10 | | Privacy policy | read, states 7 of the 8 things a reader expects | 9.3/10 | | Status page | www.planetscalestatus.com | 10/10 | | Changelog | published | 10/10 | | security.txt | not found | 0/10 | The MCP server answers at mcp.pscale.dev, a second domain. PlanetScale's own docs name the host, and its response headers name Gram, Speakeasy's hosting platform. `terms` is the Terms of Service (last updated 25 August 2026), which the Website Terms of Service name as governing the product. The website terms at /legal/siteterms are a separate document. The Privacy Policy (last updated 23 July 2026) names PlanetScale Inc. and says data processed for a customer as a processor is governed by the DPA, which was not read. planetscale.com/.well-known/security.txt returns 404. The docs publish a vulnerability disclosure policy with security@planetscale.com. The site footer and the terms name PlanetScale, Inc., 535 Mission Street, San Francisco. RDAP for planetscale.com gives a registration date of 2011-10-06 and Squarespace Domains II LLC as registrar. robots.txt on planetscale.com allows every path with `Content-Signal: ai-input=yes`. robots.txt on mcp.pscale.dev, www.planetscalestatus.com and registry.modelcontextprotocol.io answered 404, and on rdap.verisign.com 400. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service** (https://planetscale.com/legal/agreement), read 2026-10-09, gives no date, states 6 of the 7 things a reader expects. - Not found in the text. Gives the date it was last updated. - Names the governing law or courts. Disputes go to the courts of San Francisco, California. - States a limit on its liability. Rules out indirect and consequential losses, with no cap named in this sentence. - Says how changes to the terms are announced. Gives thirty days of notice before a change. - Also in the text (2026-10-08). PlanetScale may audit the facilities, computers and records of the customer and its end users, itself or through an accounting firm, to confirm compliance. "PlanetScale shall have the right to conduct and/or direct an independent accounting firm to conduct, during normal business hours, an audit of Customer’s and/or End User’s facilities, computers and records" - Also in the text (2026-10-08). After termination the customer may export its content, and PlanetScale has no duty to keep that content. "Customer may export Customer Content in accordance with the Documentation, and PlanetScale is not obligated to retain Customer Content following termination of this Agreement." - Also in the text (2026-10-08). PlanetScale may refer to its relationship with the customer in marketing material, on its website, with analysts and reporters, and in regulatory filings. "PlanetScale will be permitted to reference its relationship with Customer on its marketing material, website, during discussions with analysts and reporters and in customer briefings and regulatory filings." **Privacy policy** (https://planetscale.com/legal/privacy), read 2026-10-09, gives no date, states 7 of the 8 things a reader expects. - To know. Says it sells personal data or shares it for advertising. "We share personal information with advertising partners that display targeted advertisements to users around the web." - Not found in the text. Gives the date it was last updated. - Says how long data is kept. For as long as needed, with no period named. - Gives a privacy contact. privacy@planetscale.com. - Says where data is transferred or stored. Relies on the Data Privacy Framework. ## Live (updated 2026-10-10 05:39 UTC) - Right now: up, HTTP 401, 480 ms, checked 2026-10-10 05:39 UTC (mcp-initialize on `https://mcp.pscale.dev/mcp/planetscale`, asks for auth) - Uptime 24h 100.0% (143 probes) · 30 days 100.0% (143 probes) · p50 476 ms · p95 541 ms - Vendor status page: none, All Systems Operational - mcp-registry `io.github.planetscale/mcp-server` 1.0.0 - Watching changelog - Watching pricing - Watching privacy - Watching terms - Tools: the endpoint asks for credentials before listing them (checked 2026-10-09 21:40 UTC) - Always current: https://www.anchorterminal.com/api/v1/live/planetscale-mcp.json ## Probe metrics Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score. ## Prices | Item | Price | Unit | Note | | --- | --- | --- | --- | | Postgres PS-5, single node | $5 | per month (plan) | AWS us-east-1, storage, backups and egress extra | | Postgres PS-5, primary and two replicas | $15 | per month (plan) | AWS us-east-1, storage, backups and egress extra | | Vitess PS-10, primary and two replicas | $39 | per month (plan) | AWS us-east-1, storage extra | Across all listings: https://www.anchorterminal.com/prices/index.md ## Strengths - OAuth scopes grant no, read-only or full access per organisation or per database, and administrators can cap query access for all members since 8 October 2026 - Each query uses a database credential created for that call and deleted afterwards, and read queries run under a reader role - An insights-only endpoint omits `planetscale_execute_read_query` and `planetscale_execute_write_query` - The 13 tools published as source carry `readOnlyHint` and `destructiveHint`, checked by a test in the repository - Published SLA of 99.99 per cent for single-region and 99.999 per cent for multi-region clusters, with service credits ## Weaknesses - DELETE and DDL confirmation is a `confirm_destructive` flag the model sets, not a prompt the client shows the person - The write-query check matches the start of the statement by regular expression, so a statement behind a leading comment or a type it does not list is not matched, per the source - No rate limit for the MCP server or the API was found. The OpenAPI file lists 429 with no figures - No free tier. The billing docs say every plan needs a payment method on file - The hosted server and 12 of its 25 tools are closed. The repository has no tags, changelog or CI workflow - PlanetScale's website terms forbid robots and other automatic retrieval of the site. Recorded as a fact, and it matters before any probe is run ## Before you call it (notes for agents) 1. Use `https://mcp.pscale.dev/mcp/planetscale-insights-only` when the task needs no SQL. It omits both query tools 2. Pass `organization`, `database` and `branch` on every query call. Record them in `AGENTS.md` to skip the listing calls 3. Show the person the exact DELETE or DDL statement and get approval before setting `confirm_destructive: true` 4. Keep queries under 50 seconds and add your own `LIMIT`. The query tools cancel at 50 seconds and return every row 5. For a service token send `Authorization: Bearer pscale_tkn_...` with the secret only. The `id:secret` form is rejected ## Connect Claude Code: ```bash claude mcp add --transport http "planetscale" https://mcp.pscale.dev/mcp/planetscale ``` MCP client configuration: ```json { "mcpServers": { "planetscale": { "url": "https://mcp.pscale.dev/mcp/planetscale" } } } ``` Headless / CI: ```json { "mcpServers": { "planetscale": { "headers": { "Authorization": "Bearer ${env:PLANETSCALE_API_TOKEN}" }, "url": "https://mcp.pscale.dev/mcp/planetscale" } } } ``` Through letme (picks today, calling later): https://letme.dev/planetscale-mcp. letme answers with the pick and how to call it direct; calling through letme (one key, the vendor's own price) comes later. How it works: https://www.anchorterminal.com/letme/index.md ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | Supabase API + MCP | BB | 75.6 | 45 | db.sql, db.admin | no | https://www.anchorterminal.com/tools/supabase-mcp.md | | Postgres MCP Pro | F | 36.7 | 928 | db.sql, db.admin | no | https://www.anchorterminal.com/tools/postgres-mcp-pro.md | | MongoDB MCP Server | A | 79.9 | 10 | db.admin | no | https://www.anchorterminal.com/tools/mongodb-mcp.md | | ClickHouse MCP Server | B | 64.6 | 345 | db.sql | no | https://www.anchorterminal.com/tools/clickhouse-mcp-server.md | | Render MCP Server | B | 63.6 | 388 | db.sql | no | https://www.anchorterminal.com/tools/render-mcp-server.md | | Atlan | B | 62.5 | 426 | db.sql | no | https://www.anchorterminal.com/tools/atlan.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md ## Notable - 25 tools on one hosted endpoint, https://mcp.pscale.dev/mcp/planetscale, with an insights-only variant at https://mcp.pscale.dev/mcp/planetscale-insights-only that omits both SQL tools (source: ) - Thirteen tools are public as TypeScript under Apache-2.0. The README says the rest are generated from the PlanetScale OpenAPI file and are not in the repository (source: ) - Since 8 October 2026 organisation administrators can set MCP query access to none, read-only or read and write for new OAuth authorisations. It does not limit service tokens (source: ) - Write-query rules in the source. TRUNCATE and UPDATE or DELETE without WHERE or with an always-true WHERE are blocked, and DELETE and DDL need `confirm_destructive: true` (source: ) - Read and write queries are cancelled at 50 seconds, and Postgres reads run under an ephemeral `pg_read_all_data` role that obeys row-level security (source: ) - Three tools read or change the organisation's payment method. `planetscale_update_payment_method` returns a Stripe Checkout link and never takes card details (source: ) - The local `pscale mcp` server in the PlanetScale CLI has been removed in favour of the hosted server (source: ) - The pricing page's Markdown twin carries a block of rules addressed to AI agents and a public read-only Postgres connection string for prices. We recorded it as a fact, did not connect and did not act on it (source: ) - The endpoint answered an unauthenticated `initialize` with 401 and an OAuth protected-resource pointer. Its response headers name Gram, Speakeasy's MCP hosting platform (source: ) - #5 of 12 in Best database, file and memory tools for AI agents: https://www.anchorterminal.com/best/data/index.md - All 43 databases comparisons: https://www.anchorterminal.com/compare/data/index.md ## Compare - [ClickHouse MCP Server vs PlanetScale MCP Server](https://www.anchorterminal.com/compare/clickhouse-mcp-server-vs-planetscale-mcp.md): B 64.6 vs B 66.4 - [PlanetScale MCP Server vs Postgres MCP Pro](https://www.anchorterminal.com/compare/planetscale-mcp-vs-postgres-mcp-pro.md): B 66.4 vs F 36.7 - [PlanetScale MCP Server vs PostgreSQL (archived MCP reference server)](https://www.anchorterminal.com/compare/planetscale-mcp-vs-postgres-reference-server-archived.md): B 66.4 vs F 18.4 - [PlanetScale MCP Server vs Snowflake-managed MCP server](https://www.anchorterminal.com/compare/planetscale-mcp-vs-snowflake-managed.md): B 66.4 vs C 56.4 - [PlanetScale MCP Server vs Supabase API + MCP](https://www.anchorterminal.com/compare/planetscale-mcp-vs-supabase-mcp.md): B 66.4 vs BB 75.6 - [MongoDB MCP Server vs PlanetScale MCP Server](https://www.anchorterminal.com/compare/mongodb-mcp-vs-planetscale-mcp.md): A 79.9 vs B 66.4 - [PlanetScale MCP Server vs Redis MCP](https://www.anchorterminal.com/compare/planetscale-mcp-vs-redis-mcp.md): B 66.4 vs C 55.7 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on planetscale.com or one of its subdomains, or the README of github.com/planetscale/mcp-server. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "planetscale-mcp", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify HTML badge: ```html PlanetScale MCP Server on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![PlanetScale MCP Server on Anchor Terminal](https://www.anchorterminal.com/badges/planetscale-mcp.svg)](https://www.anchorterminal.com/tools/planetscale-mcp) ``` Plain link: ```html PlanetScale MCP Server on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say PlanetScale MCP Server is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/planetscale-mcp-dark.png - Light: https://www.anchorterminal.com/assets/share/planetscale-mcp-light.png