Lets an AI client manage security findings, triage issues, and generate remediation prompts using the Sourcery API.
Also known as abyssbugg/sourcery-agent-bundle, sourcery-agent-bundle, @abyssbugg/sourcery
- Stars
- 0
- Tools
- 12
- Downloads, 30 days
- 304
- Latest version
- 0.2.1
- Last commit
- Oct 1, 2026
- License
- MIT
What is Sourcery MCP?
Sourcery lets an AI client manage security findings, triage issues, and generate remediation prompts using the Sourcery API. It exposes 12 tools, such as sourcery_capabilities, sourcery_security_snapshot, sourcery_list_findings.
Summary generated from the project's README
About Sourcery MCP server
Sourcery provides an MCP server designed for developers and security engineers who need to manage security findings through an AI client. It connects to the Sourcery Team-plan REST API to allow agents to triage issues, view statistics, and generate remediation instructions. The server is distributed as an npm package and can be run locally via stdio or as a streamable HTTP service.
Users must provide a SOURCERY_API_KEY to access the underlying security data. The server includes twelve specific tools, such as sourcery_list_findings for retrieving issues with various filters and sourcery_build_fix_prompt for creating minimal-change agent prompts. It also supports bulk updates for up to 100 finding or group IDs at a time. This implementation uses a pinned OpenAPI snapshot to ensure the tool surface remains consistent with the verified API operations.
This bundle is compatible with a wide range of environments including Claude Code, Cursor, ChatGPT desktop, and VS Code. It can be installed using npx or through host-specific scripts provided in the package.
Written from the project's README. Every use case is checked against a quote from it.
How to install Sourcery MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Sourcery MCP in Claude Code
$ claude mcp add --env 'SOURCERY_API_KEY=<YOUR_SOURCERY_API_KEY>' sourcery-agent-bundle -- npx -y @abyssbugg/sourceryInstall Sourcery MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"sourcery-agent-bundle": {
"command": "npx",
"args": [
"-y",
"@abyssbugg/sourcery"
],
"env": {
"SOURCERY_API_KEY": "<YOUR_SOURCERY_API_KEY>"
}
}
}
}Install Sourcery MCP in VS Code
.vscode/mcp.json
{
"servers": {
"sourcery-agent-bundle": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@abyssbugg/sourcery"
],
"env": {
"SOURCERY_API_KEY": "<YOUR_SOURCERY_API_KEY>"
}
}
}
}Install Sourcery MCP in VS Code CLI
$ code --add-mcp '{"name":"sourcery-agent-bundle","type":"stdio","command":"npx","args":["-y","@abyssbugg/sourcery"],"env":{"SOURCERY_API_KEY":"<YOUR_SOURCERY_API_KEY>"}}'Install Sourcery MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"sourcery-agent-bundle": {
"command": "npx",
"args": [
"-y",
"@abyssbugg/sourcery"
],
"env": {
"SOURCERY_API_KEY": "<YOUR_SOURCERY_API_KEY>"
}
}
}
}Install Sourcery MCP in Codex
$ codex mcp add sourcery-agent-bundle --env 'SOURCERY_API_KEY=<YOUR_SOURCERY_API_KEY>' -- npx -y @abyssbugg/sourceryInstall Sourcery MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.sourcery-agent-bundle] command = "npx" args = ["-y", "@abyssbugg/sourcery"] [mcp_servers.sourcery-agent-bundle.env] SOURCERY_API_KEY = "<YOUR_SOURCERY_API_KEY>"
Install Sourcery MCP in Gemini CLI
$ gemini mcp add -s user -e 'SOURCERY_API_KEY=<YOUR_SOURCERY_API_KEY>' sourcery-agent-bundle npx -- -y @abyssbugg/sourceryInstall Sourcery MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"sourcery-agent-bundle": {
"command": "npx",
"args": [
"-y",
"@abyssbugg/sourcery"
],
"env": {
"SOURCERY_API_KEY": "<YOUR_SOURCERY_API_KEY>"
}
}
}
}Started by HostedMCP on 16 Nov 2026
We ran this command for @abyssbugg/sourcery 0.2.4 in an isolated container with no network and no keys. It answered and listed 12 tools.
Sourcery MCP tools 12
Read from the server with tools/listsourcery_capabilitiesReturn the verified Sourcery integration boundary for this bundle.
sourcery_security_snapshotTriage overview: counts by status/severity plus the first page of active issues.
sourcery_list_findingsList security issues with spec filters; pass a previous `next_cursor` to page.
sourcery_get_findingFetch a single security issue (full record incl. source snippet and dependency graph).
sourcery_get_security_countsAggregate issue counts by status and severity.
sourcery_bulk_update_findingsBulk-update issue status/severity (max 100 ids; SOLVED cannot be set manually). Returns `updated_ids` plus `failed` entries with reason `not_found` or `not_eligible`.
sourcery_list_groupsList security issue groups (same filters as findings; groups aggregate one rule/package).
sourcery_get_groupFetch a single issue group including all its issues and any linked tracker task.
sourcery_get_group_countsAggregate group counts by status and severity.
sourcery_bulk_update_groupsBulk-update groups (max 100 ids); a group updates when at least one issue changes.
sourcery_build_fix_promptBuild a minimal-change agent prompt from a Sourcery finding object. Handles DEPENDENCY findings via `fixed_versions` + `manifest_file_path` and renders the dependency chain when `dependency_graph` is present.
sourcery_api_requestCompatibility bridge: call one of the eight verified operations directly. Prefer the typed tools. The path allow-list is enforced in the client; anything outside the pinned OpenAPI surface is rejected before a request is made.
| sourcery_capabilities | Return the verified Sourcery integration boundary for this bundle. | |
| sourcery_security_snapshot | Triage overview: counts by status/severity plus the first page of active issues. | |
| sourcery_list_findings | List security issues with spec filters; pass a previous `next_cursor` to page. | |
| sourcery_get_finding | Fetch a single security issue (full record incl. source snippet and dependency graph). | |
| sourcery_get_security_counts | Aggregate issue counts by status and severity. | |
| sourcery_bulk_update_findings | Bulk-update issue status/severity (max 100 ids; SOLVED cannot be set manually). Returns `updated_ids` plus `failed` entries with reason `not_found` or `not_eligible`. | |
| sourcery_list_groups | List security issue groups (same filters as findings; groups aggregate one rule/package). | |
| sourcery_get_group | Fetch a single issue group including all its issues and any linked tracker task. | |
| sourcery_get_group_counts | Aggregate group counts by status and severity. | |
| sourcery_bulk_update_groups | Bulk-update groups (max 100 ids); a group updates when at least one issue changes. | |
| sourcery_build_fix_prompt | Build a minimal-change agent prompt from a Sourcery finding object. Handles DEPENDENCY findings via `fixed_versions` + `manifest_file_path` and renders the dependency chain when `dependency_graph` is present. | |
| sourcery_api_request | Compatibility bridge: call one of the eight verified operations directly. Prefer the typed tools. The path allow-list is enforced in the client; anything outside the pinned OpenAPI surface is rejected before a request is made. |
Configuration
SOURCERY_API_KEYRequiredSecretSourcery Team-plan API key with security scanning enabled
| Name | Description | |
|---|---|---|
| SOURCERY_API_KEY | Sourcery Team-plan API key with security scanning enabled | RequiredSecret |
Automated checks
Ran Nov 13, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledPass
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHubSourcery Agent Bundle
A hybrid plugin bundle for agent-driven Sourcery security workflows: an MCP server (12 tools over Sourcery's public security API, pinned OpenAPI snapshot), two Agent Skills, and adapters for Claude Code, Cursor, Codex/ChatGPT, VS Code, Devin, Grok (CLI + Bot), Amp, Hermes, OpenClaw, and Rovo Dev CLI. The server ships as the npm package @abyssbugg/sourcery — most hosts just register npx -y @abyssbugg/sourcery@latest. See docs/COMPATIBILITY.md for per-host install steps.
What is confirmed
Sourcery's current docs say the only public API is a Team-plan REST API for security findings. The documented API base is https://api.sourcery.ai/api, and the first documented request is:
curl https://api.sourcery.ai/api/v1/security-issues \
-H "Authorization: Bearer $SOURCERY_API_KEY"
Verified and pinned. The live OpenAPI document (https://api.sourcery.ai/api/openapi.json) is committed as a snapshot at openapi/sourcery-openapi.json:
- Info:
Sourcery API 0.1.0 (OpenAPI 3.1.0) - Fetched: 2026-09-10
- SHA-256:
9fdb45e657a6406c86ea0d0def2963d534e20bec1a9c88f7d62dbc2e6807f877
Every tool and the client allow-list are wired from that snapshot. The verified surface is exactly eight operations:
| Method | Path | Purpose |
|---|---|---|
| GET | /v1/security-issues |
List issues (filters + cursor pagination) |
| GET | /v1/security-issues/stats |
Counts by status and severity |
| GET | /v1/security-issues/{id} |
Fetch one issue |
| PATCH | /v1/security-issues |
Bulk update (max 100 ids) |
| GET | /v1/security-issue-groups |
List groups (same filters) |
| GET | /v1/security-issue-groups/stats |
Counts by status and severity |
| GET | /v1/security-issue-groups/{id} |
Fetch one group including its issues |
| PATCH | /v1/security-issue-groups |
Bulk update groups (max 100 ids) |
Why the Sourcery API + Git connector split
Sourcery's PR review controls are currently documented as GitHub/GitLab comment or label commands (review, summary, guide, title, resolve, dismiss, create issue) rather than public REST endpoints. Those actions are therefore best implemented through your GitHub/GitLab connector, while Sourcery is used for security findings.
Bundle shape
Repo root = plugin root. The portable core (plugin.json + skills/ + mcp.json) follows the Agent Plugins 1.0.0 standard, which Cursor and OpenAI (Codex, ChatGPT desktop) load natively; the other files are thin per-host adapters.
sourcery-agent-bundle/
plugin.json # Agent Plugins core manifest
mcp.json # portable stdio wiring -> bin/sourcery
skills/
sourcery-triage/SKILL.md # findings triage workflow
sourcery-remediate/SKILL.md # minimal-change fix workflow
bin/
sourcery # launcher: dist/cli.js when built, else npx @abyssbugg/sourcery
agents/
sourcery-triager.md # read-only triage sub-agent (Claude format)
.claude-plugin/plugin.json # Claude Code manifest + userConfig API key
.mcp.json # Claude Code MCP wiring (npx)
.agents/plugins/marketplace.json # Codex/ChatGPT local marketplace entry
scripts/
install-rovodev.sh # Rovo Dev CLI wiring (mcp.json + skills)
install-local-hosts.sh # grok, amp, hermes, openclaw, VS Code, Devin
examples/
mcp.http.json # remote deployment template
hooks/ # optional hooks example (SessionStart echo; not enabled)
docs/
COMPATIBILITY.md # per-host setup matrix
grok-bot-skill.md # paste-in skill for Grok Bot
openapi/
sourcery-openapi.json # pinned spec snapshot (SHA-256 above)
src/ # TypeScript: MCP server + findings CLI (@abyssbugg/sourcery)
constants.ts # pinned facts: operations, enums, spec hash
tests/ # TypeScript tests (constants drift pin, tools, client)
python/ # Python reference implementation (server, client, prompts)
src/sourcery_agent/
tests/
package.json # npm package manifest (@abyssbugg/sourcery)
.env.example
README.md
Tools
sourcery_security_snapshot: counts by status/severity plus the first page of active issues — start here for a triage overview.sourcery_list_findings: list issues withrepository_ids,issue_types,statuses,search,limit,cursor.sourcery_get_finding: fetch one issue (full record incl. source snippet and dependency graph).sourcery_get_security_counts: aggregate counts by status and severity.sourcery_bulk_update_findings: bulk status/severity changes (≤100 ids;SOLVEDis scanner-owned and rejected).sourcery_list_groups,sourcery_get_group,sourcery_get_group_counts,sourcery_bulk_update_groups: the same capabilities for issue groups.sourcery_build_fix_prompt: builds the Sourcery-style minimal-change agent prompt from a finding; the DEPENDENCY path usesfixed_versions+manifest_file_pathand renders the dependency chain.sourcery_capabilities: describes the verified surface, spec pin, and enum values.sourcery_api_request: compatibility bridge restricted to the eight verified operations.
CLI
npx -y @abyssbugg/sourcery@latest snapshot # counts + first page of active findings
npx -y @abyssbugg/sourcery@latest list --status ACTIVE --limit 50 # filterable list
npx -y @abyssbugg/sourcery@latest get 1234 # one finding in full
npx -y @abyssbugg/sourcery@latest fix-prompt 1234 # minimal-change agent prompt
Inside an enabled plugin host, bin/sourcery runs the same CLI (it prefers a locally built dist/cli.js and otherwise falls back to npx). Add --json to any query command for scripting.
Setup
Requirements: Node 20+. Most hosts register the MCP server directly:
export SOURCERY_API_KEY='...'
npx -y @abyssbugg/sourcery@latest # stdio MCP server (no args)
npx -y @abyssbugg/sourcery@latest http # Streamable HTTP (127.0.0.1:8765/mcp)
Or install it as a plugin bundle — one step per host (details in docs/COMPATIBILITY.md):
| Host | Quick start |
|---|---|
| Claude Code | claude --plugin-dir . — prompts for the API key on enable |
| Cursor | symlink the repo into ~/.cursor/plugins/local/, reload |
| Codex CLI / ChatGPT desktop | codex plugin marketplace add ./ |
| ChatGPT web | run npx -y @abyssbugg/sourcery@latest http behind HTTPS, add via developer mode |
| VS Code / Grok / Amp / Hermes / OpenClaw | scripts/install-local-hosts.sh (idempotent; registers plugin, MCP, and skills) |
| Devin | skill links via the installer; devin plugins install --local . for the full plugin |
| Grok Bot | paste-in skill from docs/grok-bot-skill.md |
| Rovo Dev CLI | scripts/install-rovodev.sh |
For development and tests, see the Python reference implementation (its suite doubles as the bundle-packaging checker) and run npm test for the TypeScript suite. The server is built on the official MCP TypeScript SDK (@modelcontextprotocol/sdk).
Regenerating the pinned snapshot
When Sourcery publishes a spec change:
curl -sS --fail -o openapi/sourcery-openapi.json https://api.sourcery.ai/api/openapi.json
shasum -a 256 openapi/sourcery-openapi.json # update SPEC_SHA256 in src/constants.ts (+ python/src/sourcery_agent/constants.py, README/docs)
npm test # tests/constants.spec.ts fails on drift
Sourcery's PR review commands (review, summary, guide, title, resolve, dismiss, create issue) remain GitHub/GitLab comment or label commands — implement those through your Git provider connector, not the Sourcery REST API.
Sourcery MCP questions
How do I add Sourcery MCP to Claude Code?
Run claude mcp add --env 'SOURCERY_API_KEY=<YOUR_SOURCERY_API_KEY>' sourcery-agent-bundle -- npx -y @abyssbugg/sourcery in your terminal. Add --scope user to make it available in every project.
How do I add Sourcery MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Sourcery MCP provide?
It exposes 12 tools, including sourcery_capabilities, sourcery_security_snapshot, sourcery_list_findings, sourcery_get_finding, sourcery_get_security_counts.
How do I install the Sourcery MCP server?
You can register it using npx by running npx -y @abyssbugg/sourcery@latest for a stdio MCP server.
Can I use this to manage GitHub or GitLab PR reviews?
No, PR review controls like resolve or dismiss should be implemented through your GitHub or GitLab connector, as they are not part of the public REST API.
What authentication method does the server use?
The server requires a Sourcery API key provided via the SOURCERY_API_KEY environment variable.