{ "data": { "a": { "slug": "sourcegraph-mcp", "name": "Sourcegraph MCP Server", "vendor": "Sourcegraph, Inc.", "vendorUrl": "https://sourcegraph.com", "kind": "mcp", "category": "code", "summary": "Sourcegraph's official MCP server gives AI agents code search, file reading, code navigation and commit and diff search across the repositories indexed by a company's Sourcegraph instance. It is built into Enterprise instances at /.api/mcp.", "url": "https://www.anchorterminal.com/tools/sourcegraph-mcp", "markdownUrl": "https://www.anchorterminal.com/tools/sourcegraph-mcp.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/sourcegraph-mcp.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/sourcegraph-mcp.json", "license": "Proprietary. The server is part of the Sourcegraph Enterprise product under the Sourcegraph Terms of Service", "transports": [ "streamable-http" ], "packages": [], "auth": "mixed", "authNotes": "An admin of a Sourcegraph Enterprise instance must exist first, and access starts with a sales contract or an approved trial. On the instance, MCP clients use OAuth 2.0 with PKCE and register themselves through dynamic client registration, which is on by default and limited to the `mcp` scope. A user approves the grant in a browser. Admins can disable registration and pre-register public clients. Clients without OAuth send a Sourcegraph access token as `Authorization: token \u003ctoken\u003e`, and the token can carry the `mcp` scope. Users need the `MCP#ACCESS` permission, granted to the User role by default.", "pricing": "paid", "pricingNotes": "Enterprise plans only. The pricing page lists one plan, starting at a $16K minimum annual contract that scales with team size, bought through sales. No per-user or per-call price is published. The plan includes credits for AI tools, and `code_finder` and Deep Search draw on that entitlement. A Sourcegraph Cloud trial is available on request and subject to eligibility, with no sandbox or free tier found (checked 2026-10-08).", "priceSummary": "Paid", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the MCP docs, the authentication docs or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": 16, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://sourcegraph.com/docs/api/mcp", "registryName": "io.github.sourcegraph/mcp", "capabilities": [ "code.repo", "code.git" ], "tags": [ "official", "mcp", "hosted", "self-hosted", "enterprise", "oauth", "read-only", "code-search", "sales-led", "soc2" ], "lastRelease": "2026-09-17", "graded": true, "anchor": { "graded": true, "score": 57.5, "grade": "C", "agentReady": false, "rank": 714, "ranked": true, "rankOf": 1239, "categoryRank": 11, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 72, "maintenance": 83, "payments": 15, "reliability": 25, "schema": 71, "security": 76, "transparency": 78 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "Sixteen read-only tools search and navigate code across every repository an instance indexes, with OAuth limited to an `mcp` scope and repository permissions enforced on each call. Access needs an Enterprise contract, priced from $16,000 a year, and no request rate limits were found in the reviewed documentation.", "bestFor": "A company that already runs Sourcegraph and wants agents to search and navigate many repositories with compiler-accurate definitions and references.", "strengths": [ "All 16 documented tools read and none writes to a repository, with three endpoints so a client can load 9, 16 or 2 tools", "OAuth 2.0 with PKCE and dynamic client registration, registered clients held to the `mcp` scope, and access tokens that can carry the same scope", "Repository permissions apply to every call, and admins can gate MCP by role (`MCP#ACCESS`) or switch off single tools with `mcp.tools.disabled`", "Result limits and defaults are documented per tool, such as 1,000 directory entries, 100 commits and 200 lines for files over 128KB", "Listed in the official MCP registry as io.github.sourcegraph/mcp, with MCP changes in dated release notes through 2026" ], "weaknesses": [ "Enterprise plans only, from a $16,000 minimum annual contract through sales. A Cloud trial is by request and subject to eligibility", "No request rate limits, 429 behaviour or tool error catalogue found in the reviewed documentation", "`code_finder` and Deep Search draw on the instance's credit entitlement and return an error once the quota is used up", "No guidance on prompt injection from repository content was found, although every search and file tool returns such content", "sourcegraph.com/.well-known/security.txt returns 404, and the bug bounty on HackerOne is invite-only" ], "agentNotes": [ "Connect to https://\u003cinstance\u003e/.api/mcp for the nine core tools. Use /.api/mcp/all for `go_to_definition`, `find_references`, `nls_search` and `compare_revisions`", "Request only the `mcp` scope in OAuth. Any other scope on the MCP resource fails with `invalid_scope`", "Without OAuth, send `Authorization: token \u003caccess token\u003e` and create the token with the `mcp` scope and an expiry", "Call `list_repos` first and name the repository in every `code_finder` task. It declines broad searches across repositories", "Read large files with `startLine` and `endLine`. Files over 128KB return only the first 200 lines" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 57.5 } ], "editorialScores": { "ergonomics": 72, "maintenance": 83, "payments": 15, "reliability": 25, "schema": 71, "security": 76, "transparency": 65 }, "provenanceScore": 90, "checked": { "categories": { "ergonomics": "2026-10-08", "maintenance": "2026-10-08", "payments": "2026-10-08", "reliability": "2026-10-08", "schema": "2026-10-08", "security": "2026-10-08", "transparency": "2026-10-08" }, "last": "2026-10-08", "oldest": "2026-10-08", "stale": false, "staleAfterDays": 90 } }, "connect": { "claudeCode": "claude mcp add --transport http sourcegraph https://sourcegraph.example.com/.api/mcp", "config": { "mcpServers": { "sourcegraph": { "type": "http", "url": "https://sourcegraph.example.com/.api/mcp" } } }, "headless": { "mcpServers": { "sourcegraph": { "headers": { "Authorization": "token ${SOURCEGRAPH_ACCESS_TOKEN}" }, "type": "http", "url": "https://sourcegraph.example.com/.api/mcp" } } } }, "letme": { "capability": "https://letme.dev/code.repo", "tool": "https://letme.dev/sourcegraph-mcp" }, "area": "developer", "provenance": { "legalEntity": "Sourcegraph, Inc.", "domain": "sourcegraph.com", "domainRegistered": "2012-11-25", "endpointOnVendorDomain": true, "terms": "https://sourcegraph.com/terms/tos", "privacy": "https://sourcegraph.com/terms/privacy", "statusPage": "https://sourcegraphstatus.com", "changelog": "https://sourcegraph.com/changelog", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The Terms of Service (last modified 22 July 2026) name Sourcegraph, Inc., 548 Market St PMB 20739, San Francisco, CA 94104-5401, and govern all Sourcegraph products. Enterprise licences are bought with an order form under these terms.", "The Privacy Policy (last modified 12 June 2026) says it does not cover user content such as customer code, which Sourcegraph processes as a data processor under the customer agreement and the DPA at sourcegraph.com/terms/dpa.", "The endpoint is on the customer's own instance. Sourcegraph Cloud instances are single-tenant, and the terms describe trial instances at \u003corganisation\u003e.sourcegraph.com. A self-hosted instance answers on the customer's domain.", "sourcegraph.com/.well-known/security.txt and /security.txt both returned 404 on 2026-10-08. The security portal sends reports to security@sourcegraph.com.", "The site footer links System status to https://sourcegraphstatus.com. The host did not resolve from our network on 2026-10-08, so the page is unread.", "RDAP for sourcegraph.com gives a registration date of 2012-11-25." ], "score": 90 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/sourcegraph-mcp.json", "live": { "slug": "sourcegraph-mcp", "vendorStatus": { "page": "https://sourcegraphstatus.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-31T00:21:17.53035872Z" }, "versions": [ { "registry": "mcp-registry", "name": "io.github.sourcegraph/mcp", "version": "0.1.0", "seenAt": "2026-10-30T14:54:40.546478788Z" } ], "securityTxt": { "url": "https://sourcegraph.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-30T15:38:13.539042928Z" }, "domain": { "domain": "sourcegraph.com", "registered": "2012-11-25", "source": "https://rdap.verisign.com/com/v1/domain/sourcegraph.com", "checkedAt": "2026-10-25T13:56:16.858044885Z" }, "pages": [ { "url": "https://sourcegraph.com/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-30T05:48:50.56614509Z", "changedAt": "2026-10-30T05:48:50.56614509Z", "fingerprint": "9a94c0616168" }, { "url": "https://sourcegraph.com/terms/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-30T05:48:52.967066264Z", "changedAt": "2026-10-30T05:48:52.967066264Z", "fingerprint": "cc62eaf00bb2" }, { "url": "https://sourcegraph.com/terms/tos", "kind": "terms", "status": 200, "checkedAt": "2026-10-30T05:48:55.061453895Z", "changedAt": "2026-10-30T05:48:55.061453895Z", "fingerprint": "f5ed0b2b5a9e" } ], "updatedAt": "2026-10-31T00:21:17.53035872Z" } }, "answer": "Superpowers scores 64.5 (B) on agent readiness against Sourcegraph MCP Server's 57.5 (C), and leads in 2 of 7 scored categories. Sourcegraph MCP Server leads on security \u0026 auth and transparency \u0026 trust.", "b": { "slug": "superpowers", "name": "Superpowers", "vendor": "Prime Radiant", "vendorUrl": "https://primeradiant.com/superpowers/", "kind": "framework", "category": "code", "summary": "Superpowers is an MIT-licensed library of 15 agent skills and a session-start bootstrap that steer coding agents through brainstorming, a design, a plan, test-driven implementation by subagents and code review. Its README gives install steps for 16 coding agents.", "url": "https://www.anchorterminal.com/tools/superpowers", "markdownUrl": "https://www.anchorterminal.com/tools/superpowers.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/superpowers.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/superpowers.json", "repo": "https://github.com/obra/superpowers", "license": "MIT (Copyright (c) 2025 Jesse Vincent)", "transports": [], "packages": [], "auth": "none", "authNotes": "No account, key or login of its own. It installs through each coding agent's plugin manager (Claude Code's official marketplace, the Codex, Cursor, Grok and Kimi marketplaces, or a git install from the repository) and runs with whatever model access and permissions that agent already has.", "pricing": "free", "pricingNotes": "Free under the MIT licence, with nothing to buy. Model usage is billed by the coding agent's provider, and the skills dispatch a subagent per task plus reviewers, which adds model calls. Prime Radiant takes enquiries for enterprise support at sales@primeradiant.com, with no published price.", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "evidence": "No machine payment protocol in the repository or on primeradiant.com, read on 2026-10-30. The project sells nothing per call.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 309222, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-30" }, "docsUrl": "https://github.com/obra/superpowers#readme", "capabilities": [ "code.git", "agent.multi-agent" ], "tags": [ "open-source", "mit", "local", "free", "agent-skills", "framework", "claude-code-plugin" ], "lastRelease": "2026-10-21", "graded": true, "anchor": { "graded": true, "score": 64.5, "grade": "B", "agentReady": false, "rank": 408, "ranked": true, "rankOf": 1239, "categoryRank": 7, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 71, "maintenance": 83, "payments": 60, "reliability": 68, "schema": 71, "security": 58, "transparency": 68 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-30" }, "negative": -3, "negativeNotes": [ "-2: until v6.0.0 of 16 June 2026 the brainstorming visual companion, a local web server, had no authentication. The release notes say anyone who could reach the port on a shared or remote machine could read the session or inject events the agent treats as the person's input (issue #1014). Fixed with a per-session key and documented, with no report of exploitation found, so the deduction is small (https://github.com/obra/superpowers/blob/main/RELEASE-NOTES.md)", "-1: until v7.0.0 of 9 October 2026, run-hook.cmd on Windows could run a `bash.cmd` or `where.bat` planted in the current directory at session start, per the release notes. Fixed and documented (https://github.com/obra/superpowers/blob/main/RELEASE-NOTES.md)" ], "verdict": "Fifteen MIT-licensed skills that make a coding agent design, plan, test first and review before it finishes, with five releases in 90 days and dated release notes. It has no CI workflow or security policy, its bootstrap insists a skill be invoked before any reply, and its optional visual companion loads a logo from Prime Radiant's site unless disabled.", "bestFor": "A test-first development method for coding agents", "strengths": [ "Installs in one command or a marketplace click in 16 coding agents, including Claude Code's official marketplace, where it is marked Anthropic verified", "Five releases between 12 August and 21 October 2026, each with dated notes that name breaking changes, fixes and the reporters credited", "Discarding work needs the typed word 'discard', merges are confirmed first, and force pushes never happen on the agent's own initiative", "Plans, task briefs, review diffs and a progress ledger are written to files, so a controller that loses context can resume without redoing work", "Zero third-party dependencies by design, MIT licence, and the one outbound request is disclosed in the README with three opt-out variables" ], "weaknesses": [ "No CI workflow in the repository; the test suites in tests/ run only on a contributor's machine", "No SECURITY.md or published advisories, though two security fixes in 2026 (the visual companion key, a Windows hook path) are documented in release notes", "The bootstrap is injected on every session start and compaction and tells the model to invoke skills before any reply, including simple questions", "Skills are long Markdown instructions (subagent-driven-development is 19,506 bytes), with no typed inputs beyond the frontmatter name and description", "194 issues and 181 pull requests were open on 30 October 2026; 13 of the 25 newest open issues had no comment" ], "agentNotes": [ "Install it once per coding agent; each harness has its own install command, and the README says a second harness needs a second install.", "Expect brainstorming to start before any code on a build request. Say so plainly if your human partner wants a quick change done without a design document.", "Name a model on every subagent dispatch, as the skill asks; an unnamed subagent inherits the session's most expensive model.", "Set SUPERPOWERS_DISABLE_TELEMETRY=1 before using the visual companion if no request may leave the machine.", "Keep `.superpowers/sdd/` out of `git clean -fdx`; it holds the progress ledger a resumed run reads." ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 64.5 } ], "editorialScores": { "ergonomics": 71, "maintenance": 83, "payments": 60, "reliability": 68, "schema": 71, "security": 58, "transparency": 77 }, "provenanceScore": 58, "checked": { "categories": { "ergonomics": "2026-10-30", "maintenance": "2026-10-30", "payments": "2026-10-30", "reliability": "2026-10-30", "schema": "2026-10-30", "security": "2026-10-30", "transparency": "2026-10-30" }, "last": "2026-10-30", "oldest": "2026-10-30", "stale": false, "staleAfterDays": 90 } }, "connect": { "claudeCode": "/plugin install superpowers@claude-plugins-official" }, "letme": { "capability": "https://letme.dev/code.git", "tool": "https://letme.dev/superpowers" }, "area": "developer", "provenance": { "legalEntity": "Prime Radiant (no legal form or registration found on its pages); the MIT LICENSE names Jesse Vincent", "domain": "primeradiant.com", "domainRegistered": "2002-05-14", "endpointOnVendorDomain": false, "terms": "https://github.com/obra/superpowers/blob/main/LICENSE", "privacy": "", "statusPage": "", "changelog": "https://github.com/obra/superpowers/blob/main/RELEASE-NOTES.md", "securityTxt": "none", "checked": "2026-10-30", "notes": [ "The README says Superpowers is built by Jesse Vincent and the rest of the folks at Prime Radiant, and the plugin manifests name Jesse Vincent as author. The LICENSE reads Copyright (c) 2025 Jesse Vincent.", "RDAP for primeradiant.com gives a registration date of 2002-05-14 and a last change on 2026-06-16; the registration may predate the company.", "No terms or privacy policy on primeradiant.com (/privacy/ and /terms/ answer 404). The MIT licence stands in for terms.", "primeradiant.com/.well-known/security.txt and /security.txt answer 404. GitHub's security page for the repository says no security policy is set up and no advisories are published, and shows a Report a vulnerability link.", "The software runs inside the person's coding agent, so there is no vendor endpoint or status page.", "firstReleased is 9 October 2025, the date of the announcement post with install steps and the repository's creation date (created_at 2025-10-09T19:45:18Z). The earliest tag, v3.1.0, is dated 17 October 2025, and RELEASE-NOTES.md has v2.0.1 on 12 October 2025." ], "score": 58 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/superpowers.json" }, "facts": [ { "a": "MCP server", "b": "Agent framework", "name": "Kind" }, { "a": "Sourcegraph, Inc.", "b": "Prime Radiant", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "Streamable HTTP", "b": "", "name": "Transports" }, { "a": "OAuth or key", "b": "None", "name": "Auth" }, { "a": "Paid", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary. The server is part of the Sourcegraph Enterprise product under the Sourcegraph Terms of Service", "b": "MIT (Copyright (c) 2025 Jesse Vincent)", "name": "Licence" }, { "a": "16", "b": "none", "name": "Tools exposed" }, { "a": "yes", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "io.github.sourcegraph/mcp", "b": "not listed", "name": "MCP registry" }, { "a": "2026-09-17", "b": "2026-10-21", "name": "Last release" }, { "a": "2026-07-22", "b": "couldn't be read", "name": "Terms last updated" }, { "a": "2026-06-12", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "b": "couldn't be read", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "couldn't be read", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "couldn't be read", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "couldn't be read", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "couldn't be read", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "309k stars", "name": "Popularity" } ], "faq": [ { "answer": "Superpowers scores 64.5 (B) on agent readiness against Sourcegraph MCP Server's 57.5 (C), and leads in 2 of 7 scored categories. Sourcegraph MCP Server leads on security \u0026 auth and transparency \u0026 trust.", "question": "Which is better for AI agents, Sourcegraph MCP Server or Superpowers?" }, { "answer": "No hosted endpoint is listed for Sourcegraph MCP Server. No hosted endpoint is listed for Superpowers.", "question": "Can an agent call Sourcegraph MCP Server and Superpowers without installing anything?" }, { "answer": "No open-source release is listed for Sourcegraph MCP Server. Superpowers is open source (MIT (Copyright (c) 2025 Jesse Vincent)).", "question": "Are Sourcegraph MCP Server and Superpowers open source?" } ], "goodFor": [ { "aheadOn": [ "Security \u0026 auth, 76 against 58", "Transparency \u0026 trust, 78 against 68" ], "also": [ "No incidents deducted, where Superpowers loses 3 points for them" ], "goodFor": "A company that already runs Sourcegraph and wants agents to search and navigate many repositories with compiler-accurate definitions and references.", "slug": "sourcegraph-mcp", "watchFor": "Enterprise plans only, from a $16,000 minimum annual contract through sales. A Cloud trial is by request and subject to eligibility" }, { "aheadOn": [ "Reliability, 68 against 25", "Payments \u0026 pricing, 60 against 15" ], "also": [ "No key needed to call it", "Open source" ], "goodFor": "A test-first development method for coding agents", "slug": "superpowers", "watchFor": "No CI workflow in the repository; the test suites in tests/ run only on a contributor's machine" } ], "job": { "capability": "code.git", "name": "Git operations" }, "others": [ { "json": "https://www.anchorterminal.com/compare/azure-devops-mcp-vs-sourcegraph-mcp.json", "title": "Azure DevOps MCP Server vs Sourcegraph MCP Server", "url": "https://www.anchorterminal.com/compare/azure-devops-mcp-vs-sourcegraph-mcp" }, { "json": "https://www.anchorterminal.com/compare/entire-vs-sourcegraph-mcp.json", "title": "Entire vs Sourcegraph MCP Server", "url": "https://www.anchorterminal.com/compare/entire-vs-sourcegraph-mcp" }, { "json": "https://www.anchorterminal.com/compare/github-mcp-server-vs-sourcegraph-mcp.json", "title": "GitHub MCP Server vs Sourcegraph MCP Server", "url": "https://www.anchorterminal.com/compare/github-mcp-server-vs-sourcegraph-mcp" }, { "json": "https://www.anchorterminal.com/compare/graphify-vs-sourcegraph-mcp.json", "title": "Graphify vs Sourcegraph MCP Server", "url": "https://www.anchorterminal.com/compare/graphify-vs-sourcegraph-mcp" }, { "json": "https://www.anchorterminal.com/compare/entire-vs-superpowers.json", "title": "Entire vs Superpowers", "url": "https://www.anchorterminal.com/compare/entire-vs-superpowers" }, { "json": "https://www.anchorterminal.com/compare/git-reference-server-vs-sourcegraph-mcp.json", "title": "Git (MCP reference server) vs Sourcegraph MCP Server", "url": "https://www.anchorterminal.com/compare/git-reference-server-vs-sourcegraph-mcp" }, { "json": "https://www.anchorterminal.com/compare/git-reference-server-vs-superpowers.json", "title": "Git (MCP reference server) vs Superpowers", "url": "https://www.anchorterminal.com/compare/git-reference-server-vs-superpowers" }, { "json": "https://www.anchorterminal.com/compare/graft-vs-sourcegraph-mcp.json", "title": "graft vs Sourcegraph MCP Server", "url": "https://www.anchorterminal.com/compare/graft-vs-sourcegraph-mcp" }, { "json": "https://www.anchorterminal.com/compare/graft-vs-superpowers.json", "title": "graft vs Superpowers", "url": "https://www.anchorterminal.com/compare/graft-vs-superpowers" }, { "json": "https://www.anchorterminal.com/compare/graphify-vs-superpowers.json", "title": "Graphify vs Superpowers", "url": "https://www.anchorterminal.com/compare/graphify-vs-superpowers" } ], "scores": [ { "by": 43, "edge": "superpowers", "key": "reliability", "name": "Reliability", "sourcegraph-mcp": 25, "superpowers": 68, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 0, "edge": "", "key": "schema", "name": "Schema \u0026 documentation", "sourcegraph-mcp": 71, "superpowers": 71, "weight": 13 }, { "by": 1, "edge": "sourcegraph-mcp", "key": "ergonomics", "name": "Agent ergonomics", "sourcegraph-mcp": 72, "superpowers": 71, "weight": 13 }, { "by": 18, "edge": "sourcegraph-mcp", "key": "security", "name": "Security \u0026 auth", "sourcegraph-mcp": 76, "superpowers": 58, "weight": 14 }, { "by": 45, "edge": "superpowers", "key": "payments", "name": "Payments \u0026 pricing", "sourcegraph-mcp": 15, "superpowers": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 0, "edge": "", "key": "maintenance", "name": "Maintenance \u0026 community", "sourcegraph-mcp": 83, "superpowers": 83, "weight": 7 }, { "by": 10, "edge": "sourcegraph-mcp", "key": "transparency", "name": "Transparency \u0026 trust", "sourcegraph-mcp": 78, "superpowers": 68, "weight": 7 } ], "summary": "Superpowers scores 64.5 (B) on agent readiness against Sourcegraph MCP Server's 57.5 (C), and leads in 2 of 7 scored categories. Sourcegraph MCP Server leads on security \u0026 auth and transparency \u0026 trust. Both do git operations.", "tutorials": [], "verdicts": { "sourcegraph-mcp": "Sixteen read-only tools search and navigate code across every repository an instance indexes, with OAuth limited to an `mcp` scope and repository permissions enforced on each call. Access needs an Enterprise contract, priced from $16,000 a year, and no request rate limits were found in the reviewed documentation.", "superpowers": "Fifteen MIT-licensed skills that make a coding agent design, plan, test first and review before it finishes, with five releases in 90 days and dated release notes. It has no CI workflow or security policy, its bootstrap insists a skill be invoked before any reply, and its optional visual companion loads a logo from Prime Radiant's site unless disabled." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/sourcegraph-mcp-vs-superpowers", "json": "https://www.anchorterminal.com/compare/sourcegraph-mcp-vs-superpowers.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/sourcegraph-mcp-vs-superpowers.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/sourcegraph-mcp-vs-superpowers.min.md" }, "markdown": "Superpowers scores 64.5 (B) on agent readiness against Sourcegraph MCP Server's 57.5 (C), and leads in 2 of 7 scored categories. Sourcegraph MCP Server leads on security \u0026 auth and transparency \u0026 trust. Both do git operations.\n\n- Sourcegraph MCP Server: grade C, 57.5/100, rank #714 of 1239. Markdown https://www.anchorterminal.com/tools/sourcegraph-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/sourcegraph-mcp.json\n- Superpowers: grade B, 64.5/100, rank #408 of 1239. Markdown https://www.anchorterminal.com/tools/superpowers.md · JSON https://www.anchorterminal.com/api/v1/tools/superpowers.json\n- Best code, repository and documentation tools for AI agents: https://www.anchorterminal.com/best/code/index.md\n- All 33 code comparisons: https://www.anchorterminal.com/compare/code/index.md\n\n## Which one, for what\n\n### Sourcegraph MCP Server (C)\n\nGood for: A company that already runs Sourcegraph and wants agents to search and navigate many repositories with compiler-accurate definitions and references.\n\nAhead on:\n- Security \u0026 auth, 76 against 58\n- Transparency \u0026 trust, 78 against 68\n\nAlso in its favour:\n- No incidents deducted, where Superpowers loses 3 points for them\n\nWatch for: Enterprise plans only, from a $16,000 minimum annual contract through sales. A Cloud trial is by request and subject to eligibility\n\n### Superpowers (B)\n\nGood for: A test-first development method for coding agents\n\nAhead on:\n- Reliability, 68 against 25\n- Payments \u0026 pricing, 60 against 15\n\nAlso in its favour:\n- No key needed to call it\n- Open source\n\nWatch for: No CI workflow in the repository; the test suites in tests/ run only on a contributor's machine\n\n\n## Score by category\n\n| Category | Weight | Sourcegraph MCP Server | Superpowers | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 25 | 68 | Superpowers +43 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 71 | 71 | even |\n| Agent ergonomics | 13% (16.2 this run) | 72 | 71 | Sourcegraph MCP Server +1 |\n| Security \u0026 auth | 14% (17.5 this run) | 76 | 58 | Sourcegraph MCP Server +18 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 15 | 60 | Superpowers +45 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 83 | 83 | even |\n| Transparency \u0026 trust | 7% (8.8 this run) | 78 | 68 | Sourcegraph MCP Server +10 |\n| Negative events | ≤15 | 0 | -3 | |\n| **Total** | | **57.5 · C** | **64.5 · B** | |\n\n## Facts side by side\n\n| Fact | Sourcegraph MCP Server | Superpowers |\n| --- | --- | --- |\n| Kind | MCP server | Agent framework |\n| Vendor | Sourcegraph, Inc. | Prime Radiant |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | Streamable HTTP | |\n| Auth | OAuth or key | None |\n| Pricing | Paid | Free |\n| x402 | no | no |\n| Licence | Proprietary. The server is part of the Sourcegraph Enterprise product under the Sourcegraph Terms of Service | MIT (Copyright (c) 2025 Jesse Vincent) |\n| Tools exposed | 16 | none |\n| Read-only variant documented | yes | no |\n| llms.txt | no | no |\n| MCP registry | `io.github.sourcegraph/mcp` | not listed |\n| Last release | 2026-09-17 | 2026-10-21 |\n| Terms last updated | 2026-07-22 | couldn't be read |\n| Privacy policy last updated | 2026-06-12 | no document linked |\n| Customer content may train models | yes, with an opt-out | couldn't be read |\n| Terms restrict automated access | not found in the text | couldn't be read |\n| Terms restrict benchmarking | not found in the text | couldn't be read |\n| Terms or service can change without notice | not found in the text | couldn't be read |\n| Arbitration or class-action waiver | yes | couldn't be read |\n| Popularity | none | 309k stars |\n\n## Verdicts\n\n**Sourcegraph MCP Server.** Sixteen read-only tools search and navigate code across every repository an instance indexes, with OAuth limited to an `mcp` scope and repository permissions enforced on each call. Access needs an Enterprise contract, priced from $16,000 a year, and no request rate limits were found in the reviewed documentation.\n\n**Superpowers.** Fifteen MIT-licensed skills that make a coding agent design, plan, test first and review before it finishes, with five releases in 90 days and dated release notes. It has no CI workflow or security policy, its bootstrap insists a skill be invoked before any reply, and its optional visual companion loads a logo from Prime Radiant's site unless disabled.\n\n## Before you call either\n\n### Sourcegraph MCP Server\n\n1. Connect to https://\u003cinstance\u003e/.api/mcp for the nine core tools. Use /.api/mcp/all for `go_to_definition`, `find_references`, `nls_search` and `compare_revisions`\n2. Request only the `mcp` scope in OAuth. Any other scope on the MCP resource fails with `invalid_scope`\n3. Without OAuth, send `Authorization: token \u003caccess token\u003e` and create the token with the `mcp` scope and an expiry\n4. Call `list_repos` first and name the repository in every `code_finder` task. It declines broad searches across repositories\n5. Read large files with `startLine` and `endLine`. Files over 128KB return only the first 200 lines\n\n### Superpowers\n\n1. Install it once per coding agent; each harness has its own install command, and the README says a second harness needs a second install.\n2. Expect brainstorming to start before any code on a build request. Say so plainly if your human partner wants a quick change done without a design document.\n3. Name a model on every subagent dispatch, as the skill asks; an unnamed subagent inherits the session's most expensive model.\n4. Set SUPERPOWERS_DISABLE_TELEMETRY=1 before using the visual companion if no request may leave the machine.\n5. Keep `.superpowers/sdd/` out of `git clean -fdx`; it holds the progress ledger a resumed run reads.\n\n## Questions\n\n### Which is better for AI agents, Sourcegraph MCP Server or Superpowers?\n\nSuperpowers scores 64.5 (B) on agent readiness against Sourcegraph MCP Server's 57.5 (C), and leads in 2 of 7 scored categories. Sourcegraph MCP Server leads on security \u0026 auth and transparency \u0026 trust.\n\n### Can an agent call Sourcegraph MCP Server and Superpowers without installing anything?\n\nNo hosted endpoint is listed for Sourcegraph MCP Server. No hosted endpoint is listed for Superpowers.\n\n### Are Sourcegraph MCP Server and Superpowers open source?\n\nNo open-source release is listed for Sourcegraph MCP Server. Superpowers is open source (MIT (Copyright (c) 2025 Jesse Vincent)).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/sourcegraph-mcp-vs-superpowers.json, and with the fewest tokens: https://www.anchorterminal.com/compare/sourcegraph-mcp-vs-superpowers.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"sourcegraph-mcp\", \"b\": \"superpowers\"}`. From a terminal: `anchor compare sourcegraph-mcp superpowers`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/sourcegraph-mcp.json and https://www.anchorterminal.com/api/v1/tools/superpowers.json\n\n## Other comparisons with Sourcegraph MCP Server or Superpowers\n\n- [Azure DevOps MCP Server vs Sourcegraph MCP Server](https://www.anchorterminal.com/compare/azure-devops-mcp-vs-sourcegraph-mcp.md)\n- [Entire vs Sourcegraph MCP Server](https://www.anchorterminal.com/compare/entire-vs-sourcegraph-mcp.md)\n- [GitHub MCP Server vs Sourcegraph MCP Server](https://www.anchorterminal.com/compare/github-mcp-server-vs-sourcegraph-mcp.md)\n- [Graphify vs Sourcegraph MCP Server](https://www.anchorterminal.com/compare/graphify-vs-sourcegraph-mcp.md)\n- [Entire vs Superpowers](https://www.anchorterminal.com/compare/entire-vs-superpowers.md)\n- [Git (MCP reference server) vs Sourcegraph MCP Server](https://www.anchorterminal.com/compare/git-reference-server-vs-sourcegraph-mcp.md)\n- [Git (MCP reference server) vs Superpowers](https://www.anchorterminal.com/compare/git-reference-server-vs-superpowers.md)\n- [graft vs Sourcegraph MCP Server](https://www.anchorterminal.com/compare/graft-vs-sourcegraph-mcp.md)\n- [graft vs Superpowers](https://www.anchorterminal.com/compare/graft-vs-superpowers.md)\n- [Graphify vs Superpowers](https://www.anchorterminal.com/compare/graphify-vs-superpowers.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-31", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Sourcegraph MCP Server vs Superpowers", "url": "" } ], "description": "Superpowers scores 64.5 (B) to Sourcegraph's 57.5 (C) for git operations. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Sourcegraph MCP Server C 57.5", "Superpowers B 64.5", "scores" ], "h1": "Sourcegraph MCP Server vs Superpowers", "image": "https://www.anchorterminal.com/assets/og/compare-sourcegraph-mcp-vs-superpowers.png", "path": "/compare/sourcegraph-mcp-vs-superpowers", "published": "2026-10-01", "section": "tools", "title": "Sourcegraph vs Superpowers for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-30", "url": "https://www.anchorterminal.com/compare/sourcegraph-mcp-vs-superpowers" }, "tokens": { "markdown": 2250, "slim": 730 }, "version": 1 }