Avallon Labs MCP
Context cost warning: its tools/list is about 45,974 tokens (217 tools), 140% of a 32k context window and 23% of a 200k window, before you send a single message. Load only the tools you need, or expect most of the context to go to tool definitions. Estimate from our testing of the tool names, descriptions and input schemas, counted with cl100k_base, measured 2026-11-18 UTC. How MCP context cost adds up
Capped at 70: no passing tool call yet; the tests add up to 95. Why scores are capped
Test points add up to 95; the score is capped at 70 until a tool call passes. Not a quality or security rating. Methodology
Test points before the cap (95/100)
- Install20/20
- Handshake30/30
- Maintenance25/25
- Docs10/15
- License10/10
Tested npm @avallon-labs/mcp 69.0.0 (MIT; no source repo linked in package metadata). Installed pinned with scripts off (npm --ignore-scripts) and launched: initialize and tools/list over stdio succeeded with no credentials and listed 217 tools (217 annotated by the server: 108 read-only, 109 destructive). Real calls: 0 of 3 real function calls passed. Calls need an Avallon API key. Core tools not tested: 70 cap.
Tool-call test (2026-11-18 UTC, direct MCP stdio client, no LLM): fail. 0 of 3 real function calls passed. Calls need an Avallon API key. Evidence: local test run, Nov 18, 2026 UTC.
Transport (tested 2026-11-18 UTC): stdio
Token cost (estimate): approx. 45974 tokens, cl100k estimate (217 tools, measured 2026-11-18 UTC, version 69.0.0). This is an estimate from our testing of the tool names, descriptions and input schemas, counted with cl100k_base.
Permissions: 106 read, 85 write (state-changing), 26 unclassified · Auth: API key · Rate limit: unknown · Pricing unit: unknown
Auth: API key. Rate limit: unknown. Pricing unit: unknown.
addCaseLinks— write (state-changing)cancelCall— write (state-changing)cancelJob— write (state-changing)cancelWorkerRun— write (state-changing)changeAccess— unclassifiedcheckInboxAvailability— unclassifiedcreateAgentWebhook— write (state-changing)createApiKey— write (state-changing)createArtifact— write (state-changing)createCall— write (state-changing)createCallFeedback— write (state-changing)createCase— write (state-changing)createCaseType— write (state-changing)createCaseTypeField— write (state-changing)createChat— write (state-changing)createChatAgent— write (state-changing)createEvalBenchmark— write (state-changing)createEvaluator— write (state-changing)createExtractor— write (state-changing)createExtractorJob— write (state-changing)createExtractorWebhook— write (state-changing)createForm— write (state-changing)createFormSubmission— write (state-changing)createInbox— write (state-changing)createInboxWebhook— write (state-changing)createInformationRequest— write (state-changing)createNotificationWebhook— write (state-changing)createSchedule— write (state-changing)createSecret— write (state-changing)createTool— write (state-changing)createVoiceAgent— write (state-changing)createWorker— write (state-changing)createWorkerBenchmarks— write (state-changing)createWorkerEvalFromRun— write (state-changing)createWorkerRun— write (state-changing)createWorkerWebhook— write (state-changing)deleteArtifact— write (state-changing)deleteCallFeedback— write (state-changing)deleteCase— write (state-changing)deleteCaseTypeField— write (state-changing)deleteChatAgent— write (state-changing)deleteEmail— write (state-changing)deleteExtractor— write (state-changing)deleteInbox— write (state-changing)deleteInformationRequest— write (state-changing)deleteSchedule— write (state-changing)deleteSecret— write (state-changing)deleteTool— write (state-changing)deleteVoiceAgent— write (state-changing)deleteWebhook— write (state-changing)deleteWorker— write (state-changing)endChat— unclassifiedexchangeExternalIdentityToken— unclassifiedexecuteCode— unclassifiedgetAccess— readgetAnalyticsTimeSeries— readgetArtifact— readgetArtifactChunks— readgetArtifactStatusSummary— readgetArtifactUploadUrl— readgetBenchmark— readgetCall— readgetCallAnalytics— readgetCallEvaluation— readgetCase— readgetCaseCitations— readgetCaseType— readgetCaseTypeVersion— readgetChat— readgetChatAgent— readgetChatAgentPrompt— readgetChatEvaluation— readgetEmail— readgetEvalRun— readgetEvaluator— readgetExtract— readgetExtractCitations— readgetExtractor— readgetExtractorJob— readgetForm— readgetFormSubmission— readgetFormVersion— readgetInformationRequest— readgetMyAccess— readgetNotification— readgetOAuthUrl— readgetPartnerJwks— readgetProfile— readgetPublicChatAgent— readgetPublicFormSubmission— write (state-changing)getPublicFormSubmissionTheme— readgetSchedule— readgetSecret— readgetSessionToken— readgetTenantSettings— readgetTool— readgetToolCall— readgetToolVersion— readgetToolVersionChangeSummary— readgetVoiceAgent— readgetVoiceAgentPlaceholders— readgetVoiceAgentPrompt— readgetVoiceAgentVersion— readgetVoiceAgentVersionChangeSummary— readgetWebhook— readgetWorker— readgetWorkerPrompt— readgetWorkerRun— readgetWorkerRunMessage— readgetWorkerVersion— readgetWorkerVersionChangeSummary— readinviteTeamMember— unclassifiedlistAgentWebhooks— readlistApiKeys— readlistArtifacts— readlistCallFeedback— readlistCalls— readlistCaseLinks— readlistCaseTypeVersions— readlistCaseTypes— readlistCases— readlistChatAgents— readlistChatMessages— readlistChats— readlistDispatches— readlistEmailThreads— readlistEmails— readlistEvalBenchmarks— readlistEvalRuns— readlistEvaluators— readlistExtractorJobs— readlistExtractors— readlistExtracts— readlistFormSubmissions— readlistFormVersions— readlistForms— readlistInboxWebhooks— readlistInboxes— readlistInformationRequests— readlistJobs— readlistNotificationWebhooks— readlistNotifications— readlistSchedules— readlistSecrets— readlistTeamInvitations— readlistTeamMembers— readlistToolCalls— readlistToolVersions— readlistTools— readlistVoiceAgentVersions— readlistVoiceAgents— readlistWebhookDeliveries— readlistWebhooks— readlistWorkerEvalSuites— readlistWorkerEvals— readlistWorkerModels— write (state-changing)listWorkerRunMessages— readlistWorkerRuns— readlistWorkerVersions— readlistWorkerWebhooks— readlistWorkers— readlistenCall— unclassifiednotifyAdmin— write (state-changing)partnerLaunch— unclassifiedpostChatMessage— write (state-changing)promoteCaseTypeVersion— unclassifiedpromoteFormVersion— unclassifiedpromoteToolVersion— unclassifiedpromoteVoiceAgentVersion— unclassifiedpromoteWorkerVersion— unclassifiedrefreshSession— unclassifiedrefreshToken— unclassifiedremoveCaseLink— write (state-changing)removeMember— write (state-changing)replyToEmail— unclassifiedrequestPasswordReset— unclassifiedresendTeamInvitation— unclassifiedresetPassword— unclassifiedresolveInformationRequest— readrevokeApiKey— write (state-changing)revokeTeamInvitation— write (state-changing)runEval— unclassifiedscheduleJob— unclassifiedsearchCases— readsendEmail— write (state-changing)setWorkerEvalSuite— write (state-changing)signIn— unclassifiedsignUp— write (state-changing)submitFormSubmission— write (state-changing)testWebhook— unclassifiedupdateApiKey— write (state-changing)updateArtifactMetadata— write (state-changing)updateCallControls— write (state-changing)updateCase— write (state-changing)updateCaseType— write (state-changing)updateCaseTypeField— write (state-changing)updateChatAgent— write (state-changing)updateChatAgentPrompt— write (state-changing)updateExtractor— write (state-changing)updateForm— write (state-changing)updateInbox— write (state-changing)updateMemberRole— write (state-changing)updateSchedule— write (state-changing)updateSecret— write (state-changing)updateTenantSettings— write (state-changing)updateTool— write (state-changing)updateVoiceAgent— write (state-changing)updateVoiceAgentModels— write (state-changing)updateVoiceAgentPrompt— write (state-changing)updateWebhook— write (state-changing)updateWorker— write (state-changing)updateWorkerMcps— write (state-changing)updateWorkerPrompt— write (state-changing)uploadFile— write (state-changing)workerExecuteTool— unclassifiedworkerGetTool— unclassifiedworkerListTools— unclassified
listing-flags calls_need_key or auth_kind
Score 70/100 · Tools 217 · Token cost approx. 45,974 tokens · Compare · Last tested 2026-11-18 UTC · Version tested 69.0.0 · Package @avallon-labs/mcp
Summary: Avallon Labs MCP completed an MCP handshake without credentials and exposed 217 tools.
Evidence summary
- Handshake
- pass
- Tools listed
- 217
- Context cost
- approx. 45974 tokens, cl100k estimate (217 tools, measured 2026-11-18 UTC, version 69.0.0; an estimate) ranking · add up your servers' context cost
- API key
- Connects without a key; tool calls need one
- Tested
- 2026-11-18 UTC
Test results
| Test | Result | Points | Evidence |
|---|---|---|---|
| install | pass | 20 | npm install @avallon-labs/mcp --ignore-scripts (Node v24.22.1, Linux) succeeded in 1s. |
| handshake | pass | 30 | MCP initialize + tools/list over stdio succeeded with no credentials; 217 tools listed in 4.5s. |
| maintenance | pass | 25 | Latest release published 0 days before test. |
| docs | partial | 10 | install instructions present; mcpServers config example 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. 45974 tokens, cl100k estimate for 217 tools · about 561% 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 2026-11-18 UTC
- Install from the registry
- We connected with no credentials and asked for its tool list: it listed 217 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
Not yet checked.
Monthly roundup: MCP security issues, October 2026.
Tool list changes
Baseline recorded from the 2026-11-18 UTC test run; changes appear after the next test.
Snapshot hash (fingerprint of the tool list)
cd6b9c1c4226: SHA-256 of the canonical tool names, descriptions and input schemas. If it changes, the tool list changed.
Raw test record (JSON)
{
"name": "@avallon-labs/mcp",
"version": "69.0.0",
"registry": "npm",
"status": "working",
"tested": "2026-11-18",
"tools_count": 217,
"deprecated": false,
"archived": null,
"tests": {
"install": [
"pass",
20,
"`npm install @avallon-labs/mcp --ignore-scripts` (Node v24.22.1, Linux) succeeded in 1s."
],
"handshake": [
"pass",
30,
"MCP `initialize` + `tools/list` over stdio succeeded with no credentials; 217 tools listed in 4.5s."
],
"maintenance": [
"pass",
25,
"Latest release published 0 days before test."
],
"docs": [
"partial",
10,
"install instructions present; `mcpServers` config example present. Check of the package's own README (README shipped in npm package)."
],
"license": [
"pass",
10,
"MIT (OSI-approved)."
]
},
"testedAt": "2026-11-18T04:18:31.538Z"
}Install
npx -y @avallon-labs/mcp
Pin the version we tested
npx -y --ignore-scripts @avallon-labs/mcp@69.0.0
tested 2026-11-18 UTC. Newer versions may differ and were not tested by us.
{
"mcpServers": {
"avallon-labs-mcp": {
"command": "npx",
"args": [
"-y",
"@avallon-labs/mcp@69.0.0"
]
}
}
}Tools listed
Showing 40 of 217 names: listVoiceAgents, createVoiceAgent, getVoiceAgent, updateVoiceAgent, deleteVoiceAgent, listVoiceAgentVersions, getVoiceAgentVersion, promoteVoiceAgentVersion, getVoiceAgentVersionChangeSummary, getVoiceAgentPlaceholders, getVoiceAgentPrompt, updateVoiceAgentPrompt, updateVoiceAgentModels, updateCallControls, scheduleJob, listJobs, cancelJob, listApiKeys, createApiKey, revokeApiKey, updateApiKey, createArtifact, listArtifacts, getArtifact, deleteArtifact, getArtifactChunks, getArtifactStatusSummary, getArtifactUploadUrl, updateArtifactMetadata, signUp, signIn, requestPasswordReset, resetPassword, refreshToken, refreshSession, getOAuthUrl, getSessionToken, getPartnerJwks, partnerLaunch, listCalls.Show all 217 names
listVoiceAgents, createVoiceAgent, getVoiceAgent, updateVoiceAgent, deleteVoiceAgent, listVoiceAgentVersions, getVoiceAgentVersion, promoteVoiceAgentVersion, getVoiceAgentVersionChangeSummary, getVoiceAgentPlaceholders, getVoiceAgentPrompt, updateVoiceAgentPrompt, updateVoiceAgentModels, updateCallControls, scheduleJob, listJobs, cancelJob, listApiKeys, createApiKey, revokeApiKey, updateApiKey, createArtifact, listArtifacts, getArtifact, deleteArtifact, getArtifactChunks, getArtifactStatusSummary, getArtifactUploadUrl, updateArtifactMetadata, signUp, signIn, requestPasswordReset, resetPassword, refreshToken, refreshSession, getOAuthUrl, getSessionToken, getPartnerJwks, partnerLaunch, listCalls, createCall, getCall, cancelCall, listenCall, getCallEvaluation, getCallAnalytics, getAnalyticsTimeSeries, createCallFeedback, listCallFeedback, deleteCallFeedback, checkInboxAvailability, createInbox, listInboxes, updateInbox, deleteInbox, getEmail, deleteEmail, listEmails, listEmailThreads, replyToEmail, sendEmail, listExtractorJobs, createExtractorJob, getExtractorJob, listWorkerRuns, createWorkerRun, getWorkerRun, listWorkerRunMessages, getWorkerRunMessage, cancelWorkerRun, createWorkerEvalFromRun, runEval, listEvalRuns, getEvalRun, createEvalBenchmark, listEvalBenchmarks, getBenchmark, listWorkerEvals, createWorkerBenchmarks, listWorkerEvalSuites, setWorkerEvalSuite, createExtractor, listExtractors, getExtractor, updateExtractor, deleteExtractor, createWorker, listWorkers, getWorker, deleteWorker, updateWorker, getWorkerPrompt, updateWorkerPrompt, listWorkerModels, updateWorkerMcps, getAccess, changeAccess, getMyAccess, listWorkerVersions, getWorkerVersion, promoteWorkerVersion, getWorkerVersionChangeSummary, createWorkerWebhook, listWorkerWebhooks, listCases, createCase, searchCases, getCase, deleteCase, updateCase, getCaseCitations, addCaseLinks, listCaseLinks, removeCaseLink, createChatAgent, listChatAgents, getChatAgent, updateChatAgent, deleteChatAgent, getChatAgentPrompt, updateChatAgentPrompt, createChat, getChat, getPublicChatAgent, postChatMessage, endChat, exchangeExternalIdentityToken, listChats, listChatMessages, getChatEvaluation, getPublicFormSubmission, submitFormSubmission, getPublicFormSubmissionTheme, createForm, listForms, getForm, updateForm, listFormVersions, getFormVersion, promoteFormVersion, createFormSubmission, listFormSubmissions, getFormSubmission, getExtract, getExtractCitations, listExtracts, getProfile, listTeamMembers, inviteTeamMember, listTeamInvitations, revokeTeamInvitation, resendTeamInvitation, updateMemberRole, removeMember, getTenantSettings, updateTenantSettings, createSecret, listSecrets, getSecret, updateSecret, deleteSecret, createEvaluator, listEvaluators, getEvaluator, createSchedule, listSchedules, getSchedule, updateSchedule, deleteSchedule, listDispatches, listNotifications, getNotification, createInformationRequest, listInformationRequests, getInformationRequest, deleteInformationRequest, resolveInformationRequest, createCaseType, listCaseTypes, getCaseType, updateCaseType, listCaseTypeVersions, getCaseTypeVersion, promoteCaseTypeVersion, createCaseTypeField, updateCaseTypeField, deleteCaseTypeField, createTool, listTools, deleteTool, getTool, updateTool, executeCode, listToolVersions, getToolVersion, promoteToolVersion, getToolVersionChangeSummary, listToolCalls, getToolCall, workerListTools, workerGetTool, workerExecuteTool, notifyAdmin, uploadFile, createAgentWebhook, listAgentWebhooks, createInboxWebhook, listInboxWebhooks, createExtractorWebhook, listWebhooks, createNotificationWebhook, listNotificationWebhooks, deleteWebhook, getWebhook, updateWebhook, listWebhookDeliveries, testWebhook
Quick config
{
"mcpServers": {
"avallon-labs-mcp": {
"command": "npx",
"args": [
"-y",
"@avallon-labs/mcp"
]
}
}
}Add to config Opens the config generator with this server selected.
Setup
- Install. Run
npm install @avallon-labs/mcp --ignore-scripts(Node v24.22.1). This is the exact command we ran on 2026-11-18 UTC. - Configure. Add the mcpServers entry below to your MCP client config.
- Verify. Restart the client and check that tools/list returns tools (217 in our test).
{
"mcpServers": {
"avallon-labs-mcp": {
"command": "npx",
"args": [
"-y",
"@avallon-labs/mcp"
]
}
}
}Test history
- 2026-11-18 UTC: New
FAQ
Is Avallon Labs MCP deprecated?
No. Avallon Labs MCP was not deprecated or archived when we last tested it on 2026-11-18 UTC.
What replaces Avallon Labs MCP?
Nothing; Avallon Labs MCP is not deprecated as of 2026-11-18 UTC.
Does Avallon Labs MCP need an API key?
It connects and lists 217 tools without a key, but its tool calls need one.
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.