BLA (Blind LLM Agents)
Score = points from our five tests (install, handshake, maintenance, docs, license). Not a quality or security rating. Methodology
- Install20/20
- Handshake30/30
- Maintenance25/25
- Docs10/15
- License10/10
Tested npm bla-agents 3.2.4 (MIT; repo qybaihe/bla, 5,156 GitHub stars when checked, created 2026-10-25) through `bla-agents mcp`. Stdio, 31 tools for auditing, linting and hardening shipped JavaScript, WASM, Electron and Python artifacts, no account. Real calls on a one-file JavaScript test project: bla_discover listed the artifact, bla_audit returned an exposure report (score 81, UNPROTECTED) and bla_lint_plaintext_secrets found no cleartext secrets; bla_doctor (self-check) reported all engines ready. The tools that rewrite files (bla_harden, bla_protect, bla_encrypt_strings, bla_init and similar) were not called. The README has no MCP client config, so the Quick config below is the command we ran.
Tool-call test (2026-11-11, direct MCP stdio client, no LLM): pass. 3 of 3 read calls passed on a local test project, no key (plus 1 self-check). File-rewriting tools not called. Evidence: local test run, Nov 11, 2026.
Transport (tested 2026-11-11): stdio
Token cost (estimate): approx. 8212 tokens, cl100k estimate (31 tools, measured 2026-11-11, version 3.2.4). This is an estimate from our testing of the tool names, descriptions and input schemas, counted with cl100k_base.
Permissions: 16 read, 1 write (state-changing), 14 unclassified · Auth: none · Rate limit: unknown · Pricing unit: unknown
Auth: none. Rate limit: unknown. Pricing unit: unknown.
bla_audit— unclassifiedbla_benchmark— unclassifiedbla_bind_scope— unclassifiedbla_defend— unclassifiedbla_discover— readbla_doctor— unclassifiedbla_emit_headers— unclassifiedbla_encrypt_strings— unclassifiedbla_harden— unclassifiedbla_init— write (state-changing)bla_inspect_release— readbla_lint— unclassifiedbla_lint_bind_scope— readbla_lint_integrity_coverage— readbla_lint_js_aes_unwrap— readbla_lint_js_wasm_hydrate_dump— readbla_lint_lanes— readbla_lint_panel_derive— readbla_lint_plaintext_secrets— readbla_lint_seal— readbla_lint_wasm_params— readbla_lint_wasm_seal_xor_known_plaintext— readbla_lint_wasm_xor_mask_sidecar— readbla_polymorph_report— unclassifiedbla_protect— unclassifiedbla_rea_drift— unclassifiedbla_redteam_report— unclassifiedbla_run_lookup— readbla_verify— unclassifiedbla_verify_weave— readbla_weave_plan— read
handshake and tools listed without a recorded key or OAuth
Score 95/100 · Tools 31 · Token cost approx. 8,212 tokens · Compare · Last tested 2026-11-11 · Version tested 3.2.4 · Package bla-agents · Repo qybaihe/bla
Summary: BLA (Blind LLM Agents) completed an MCP handshake without credentials and exposed 31 tools.
Evidence summary
- Handshake
- pass
- Tools listed
- 31
- Context cost
- approx. 8212 tokens, cl100k estimate (31 tools, measured 2026-11-11, version 3.2.4; an estimate) ranking · add up your servers' context cost
- API key
- No key needed for the tools we called
- Tested
- 2026-11-11
Test results
| Test | Result | Points | Evidence |
|---|---|---|---|
| install | pass | 20 | npm install bla-agents (Node 20, Linux) succeeded in 1s. |
| handshake | pass | 30 | MCP initialize + tools/list over stdio succeeded with no credentials; 31 tools listed in 6.2s. |
| maintenance | pass | 25 | Repo pushed 0 days before test; 5,156 GitHub stars. |
| docs | partial | 10 | README over 3,000 chars; install instructions present. Check of the package's own README (README shipped in npm package). |
| license | pass | 10 | MIT (OSI-approved). |
Local-model readiness
Token cost (estimate): approx. 8212 tokens, cl100k estimate for 31 tools · about 100% of an 8k context. This is an estimate from our testing (counted with cl100k_base).
Small-model friendly (schema heuristic, not a model result): unknown.
Not tested
Small-model task runs: Not yet tested.
What we tested and what we didn't
Tested on 2026-11-11
- Install from the registry
- We connected with no credentials and asked for its tool list: it listed 31 tools (Method details: MCP
initializethentools/list) - Maintenance signals (last push, archived/deprecated status)
- Docs (README length, install and config example)
- License (OSI-approved or not)
- Token cost (estimate)
Not tested
- Security: not audited (no code review, no permission or data-flow analysis)
- Real tasks (no functional task runs yet)
- Behaviour with real credentials or a real account
- Performance, rate limits or load
- Correctness of results beyond the listed tasks
Methodology: how we test. A high score means it installs and responds, not that giving it access to your data carries no risk.
Known security issues
Checked on 2026-11-11 for version 3.2.4 against OSV, GitHub advisories, GitHub repository advisories. Scope: the package itself; dependencies not scanned.
No published advisories found in OSV and GitHub advisories for bla-agents 3.2.4 as of 2026-11-11. This is not a security audit.
Monthly roundup: MCP security issues, October 2026.
Tool list changes
Baseline recorded from the 2026-11-11 test run; changes appear after the next test.
Snapshot hash (fingerprint of the tool list)
36237ee60f36: SHA-256 of the canonical tool names, descriptions and input schemas. If it changes, the tool list changed.
Raw test record (JSON)
{
"name": "bla-agents",
"version": "3.2.4",
"registry": "npm",
"status": "working",
"tested": "2026-11-11",
"tools_count": 31,
"deprecated": false,
"archived": false,
"tests": {
"install": [
"pass",
20,
"`npm install bla-agents` (Node 20, Linux) succeeded in 1s."
],
"handshake": [
"pass",
30,
"MCP `initialize` + `tools/list` over stdio succeeded with no credentials; 31 tools listed in 6.2s."
],
"maintenance": [
"pass",
25,
"Repo pushed 0 days before test; 5,156 GitHub stars."
],
"docs": [
"partial",
10,
"README over 3,000 chars; install instructions present. Check of the package's own README (README shipped in npm package)."
],
"license": [
"pass",
10,
"MIT (OSI-approved)."
]
}
}Install
npx -y bla-agents mcp
Pin the version we tested
npx -y bla-agents@3.2.4 mcp
tested 2026-11-11. Newer versions may differ and were not tested by us.
{
"mcpServers": {
"bla-blind-llm-agents": {
"command": "npx",
"args": [
"-y",
"bla-agents@3.2.4",
"mcp"
]
}
}
}Tools listed
bla_audit, bla_benchmark, bla_bind_scope, bla_defend, bla_discover, bla_doctor, bla_emit_headers, bla_encrypt_strings, bla_harden, bla_init, bla_inspect_release, bla_lint, bla_lint_bind_scope, bla_lint_integrity_coverage, bla_lint_js_aes_unwrap, bla_lint_js_wasm_hydrate_dump, bla_lint_lanes, bla_lint_panel_derive, bla_lint_plaintext_secrets, bla_lint_seal, bla_lint_wasm_params, bla_lint_wasm_seal_xor_known_plaintext, bla_lint_wasm_xor_mask_sidecar, bla_polymorph_report, bla_protect, bla_rea_drift, bla_redteam_report, bla_run_lookup, bla_verify, bla_verify_weave, bla_weave_plan
Tool history: captured Nov 11, 2026. All tool history.
Quick config
config from our testing; README has none
{
"mcpServers": {
"bla-blind-llm-agents": {
"command": "npx",
"args": [
"-y",
"bla-agents",
"mcp"
]
}
}
}Add to config Opens the config generator with this server selected.
Setup
- Install. Run
npm install bla-agents(Node 20). This is the exact command we ran on 2026-11-11. - Configure. Add the mcpServers entry below to your MCP client config.
- Verify. Restart the client and check that tools/list returns tools (31 in our test).
{
"mcpServers": {
"bla-blind-llm-agents": {
"command": "npx",
"args": [
"-y",
"bla-agents",
"mcp"
]
}
}
}Test history
- 2026-11-11: New
Related: Troubleshooting: Protocol version mismatch (HTTP 400)
FAQ
Is BLA (Blind LLM Agents) deprecated?
No. bla-agents was not deprecated or archived when we last tested it on 2026-11-11.
What replaces BLA (Blind LLM Agents)?
Nothing; BLA (Blind LLM Agents) is not deprecated as of 2026-11-11.
Does BLA (Blind LLM Agents) need an API key?
No. It completed an MCP handshake with no credentials and listed 31 tools.
Embed the badge
Every tested server gets a free embeddable badge. It shows the current score and test date and expires after 90 days. Testing is free; payment never changes a score.