At a glance
What it does
Map HTTP routes, outbound calls, and cross-repository service dependencies from a Memtrace-indexed code graph.
Before you choose it
This is a focused workflow prompt for investigating an indexed codebase's API surface. It directs the agent to use Memtrace tools to list endpoint handlers, find outbound HTTP calls, and inspect topology edges between repositories; endpoint handler names can then be passed to symbol-context analysis.
Best for
Developers and engineering teams using Memtrace to understand REST surfaces or dependencies across services.
Common tasks
- List API endpoints in an indexed repository.
- Find outbound HTTP calls by method or path fragment.
- Map service-to-service topology after indexing the relevant repositories.
- Investigate an endpoint handler using its symbol name.
Permissions and data
Uses Memtrace's local indexed code graph to answer topology questions.
Permissions- Access to Memtrace MCP tools, including endpoint, call, and topology queries.
- Access to code repositories that you are authorized to index and analyze.
- The EULA states that source code is processed locally and indexed data remains under the user's control.
- The README says license validation, aggregate node/edge counts, and opt-out crash telemetry may generate network traffic; it says source, file paths, and symbol names are not sent.
- Memtrace MCP server.
- Potential Memtrace license-validation and telemetry services, depending on product configuration.
- No credential requirement is declared for this skill itself.
Limitations
- It depends on repositories being indexed in Memtrace.
- Cross-repository links require all relevant services to be indexed; the skill notes that repository linking may also be needed.
- It is guidance for Memtrace tools, not a standalone API scanner.
- The skill's claimed behavior and tool availability were not executed during curation.
What DSHub checked
- The supplied SKILL.md defines endpoint, HTTP-call, and topology use cases and names its required Memtrace tools.
- The source is pinned to commit 56b3abb4ddd033edc7c6f2b92294e68fb4f0742d.
- The supplied EULA covers bundled AI agent skills.
What DSHub did not check
- Installation into any host was not performed.
- No repository was indexed and no Memtrace tool call was run.
- Runtime compatibility with a particular Harness version was not declared in supplied evidence.
Pinned install
Primary action
This standalone skill does not have a DSH Plugin install action. Use its source documentation for the delivery method.
Maintainer source
Skill instructions
name: memtrace-api-topology description: "Map API endpoints, outbound HTTP calls, and cross-repo service topology in indexed source code. Use when the user asks about API endpoints, HTTP routes, fetch/client calls, REST surface, service dependencies, cross-repo dependencies, or API topology. Do not use Grep, Glob, rg, find, or manual file search for routes or HTTP calls; Memtrace maps endpoints and call edges from the indexed AST graph."
Overview
Map HTTP API surface — endpoints, outbound calls, cross-repo topology.
Quick Reference
| Tool | Required | Key optional |
|---|---|---|
find_api_endpoints |
repo_id |
method, path_contains, limit, branch |
find_api_calls |
repo_id |
method, path_contains, limit, branch |
get_api_topology |
— | repo_id, min_confidence, include_external |
Full parameter spec for every Memtrace tool: references/mcp-parameters.md (bundled at the memtrace-skills plugin root).
Steps
1–3. Endpoints, calls, topology
{ "repo_id": "memdb" }
{ "repo_id": "memdb", "method": "GET", "path_contains": "/users" }
{ "min_confidence": 0.7 }
4. Deep-dive an endpoint handler
Use handler symbol name — not symbol ID:
{ "repo_id": "memdb", "symbol": "handleGetUsers" }
Output
| Result | Carries |
|---|---|
Endpoint entry (find_api_endpoints) |
HTTP method, route path, handler symbol name (feed to get_symbol_context as symbol) |
Call entry (find_api_calls) |
HTTP method, target path, calling symbol |
Topology edge (get_api_topology) |
caller repo → handler repo, confidence 0.0–1.0 (edges below min_confidence dropped) |
Common Mistakes
| Mistake | Reality |
|---|---|
get_symbol_context(symbol_id=...) |
Use symbol (name) + repo_id |
| Cross-repo links with one repo indexed | Index all services; use link_repositories if needed |
Operate deliberately
Install and manage
Prerequisites and target Profile
Target： Codex Profile, Claude Code Profile, Cursor Profile, Deepseek Harness Profile
Delivery： Skill Files — https://raw.githubusercontent.com/syncable-dev/memtrace-public/56b3abb4ddd033edc7c6f2b92294e68fb4f0742d/plugins/memtrace-skills/skills/memtrace-api-topology/SKILL.md。
Compatibility and access
Requires an indexed repository and Memtrace MCP tools： Not declared in supplied evidence。
Review compatibility evidence ↗
Risk facts
Proprietary EULA applies; bundled skills may not be extracted, redistributed, or repurposed independently.
Evidence ↗Memtrace states that source code is processed locally; optional telemetry and external-service configuration are separately described.
Evidence ↗Evidence and editorial reviewManifest, Bundle patch, distribution and freshness
Immutable evidence
Review status and source activity
Use only with codebases you are authorized to analyze; review the proprietary EULA before copying or installing the bundled skill.
AI reviewed Sep 12, 2026, 1:49 PM UTC。GitHub facts last checked Sep 12, 2026, 1:49 PM UTC。
No material source change has been recorded since this evidence baseline.