reporecall

Reporecall is a local developer-tool and MCP server/daemon that indexes a codebase (AST parsing + hybrid keyword/vector search + call-graph expansion) and injects relevant code and persistent “memory” into Claude Code prompts via a pre-submit hook. It also provides MCP tools for searching code and storing/recalling project memories on disk.

Evaluated Mar 30, 2026 (0d ago)
Repo ↗ DevTools ai-coding code-search code-navigation mcp rag local-first tree-sitter call-graph memory
⚙ Agent Friendliness
54
/ 100
Can an agent use this?
🔒 Security
46
/ 100
Is it safe for agents?
⚡ Reliability
38
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
78
Documentation
60
Error Messages
0
Auth Simplicity
85
Rate Limits
10

🔒 Security

TLS Enforcement
40
Auth Strength
55
Scope Granularity
30
Dep. Hygiene
45
Secret Handling
60

Runs locally (localhost-only daemon) and uses a bearer token for the hook endpoint per README, which reduces exposure surface. However, explicit TLS requirements, token storage/handling, and fine-grained authorization/scopes are not documented. The tool also ingests code and may store persistent memory on disk; operators should ensure filesystem permissions are appropriate. Dependency list is moderate; no CVE status is provided.

⚡ Reliability

Uptime/SLA
0
Version Stability
65
Breaking Changes
40
Error Recovery
45
AF Security Reliability

Best When

You use Claude Code with local development on a TypeScript/JS-or-multi-language repo and want faster, context-rich retrieval (including callers/callees) with persistent local memory.

Avoid When

You need a hosted API service with network access controls, or you require guaranteed type-accurate call graph edges; also avoid when queries are too vague to anchor on indexed symbols/terms.

Use Cases

  • Speeding up code understanding for AI assistants (find symbols, callers/callees, call flows)
  • Building code navigation context for Claude Code before it answers
  • Persisting project knowledge and coding conventions across sessions via local memory files
  • Answering architectural/inventory questions with hybrid search and term expansion
  • Reducing repeated “grep chains” during interactive development

Not For

  • Handling non-code/runtime behavior debugging where dynamic tooling is required
  • Cloud-hosted multi-tenant deployments needing centralized auth/audit
  • Use cases requiring strict type-resolved call graphs beyond name-based resolution

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: bearer-token auth for local daemon hook (localhost)
OAuth: No Scopes: No

Authentication is described for the local daemon endpoint used by the prompt hook (localhost-only). No cloud/user auth flows are described.

Pricing

Free tier: No
Requires CC: No

No pricing information provided; appears local/OSS tooling installed via npm.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Name-based call-graph edges may produce false edges in languages where types/disambiguation matter.
  • Retrieval can be weak for vague queries that lack an anchor symbol/term.
  • Token-budgeted context assembly may omit low-scoring or demoted test files, affecting answers that rely on tests.
  • Index staleness should be mitigated via local file watching, but behavior depends on daemon/indexing configuration.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for reporecall.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

6533
Packages Evaluated
19870
Need Evaluation
586
Need Re-evaluation
Community Powered