Validate Formhaus form definitions and simulate multi-step paths against the real engine.
Nothing to run from here
Talonic is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
97/100
trust score
522
downloads a day
local
runs on your machine
2k
downloads in 30d
What it does
Official Talonic MCP server. Lets AI agents extract structured, schema-validated data from any document via the Model Context Protocol.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'TALONIC_API_KEY=${TALONIC_API_KEY}' --transport stdio talonic-mcp '--' npx -y @talonic/mcp
# 2 — ask your agent for something these tools do
# talonic_extract, talonic_filter, talonic_get_balance and 105 more
It needs TALONIC_API_KEY: this reads it from your environment, so export it first.
Talonic costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
TAAll 1 server
talonicdev1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Talonic as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads TALONIC_API_KEY (Your Talonic API key. Get one at https://app.talonic.com) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx TALONIC_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'TALONIC_API_KEY=${TALONIC_API_KEY}' --transport stdio talonic-mcp '--' npx -y @talonic/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: TALONIC_API_KEY — Your Talonic API key. Get one at https://app.talonic.com.. You set it in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
108 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Talonic or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 97 / 100
Release 0.1.90 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score97
Findings0 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digestf0f481aa77a63f810a974ea21d081f72d5c5a2935f68924eb8ce16af0a73ffda
Score vectorthreat 100 → client 97
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (108 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
2 of the 108 recovered tools are registered only when opts.includeGenericExecutor === false is false (dist/http-server.js:6448) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 34.
4 of the 108 recovered tools are registered only when options.includeGrowthTools holds (dist/http-server.js:7103) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 34.
5 of the 108 recovered tools are registered only when options.includeAdminAgentTaskTools holds (dist/http-server.js:7106) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 34.
13 of the 108 recovered tools are registered only when options.includeContractsTools holds (dist/http-server.js:7109) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 34.
8 of the 108 recovered tools are registered only when options.includeApTools holds (dist/http-server.js:7112) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 34.
16 of the 108 recovered tools are registered only when options.includeDocGenTools holds (dist/http-server.js:7115) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 34.
12 of the 108 recovered tools are registered only when options.includePartiesTools holds (dist/http-server.js:7118) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 34.
8 of the 108 recovered tools are registered only when options.includeMasterRecordsTools holds (dist/http-server.js:7121) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 34.
6 of the 108 recovered tools are registered only when options.includeSubmissionsTools holds (dist/http-server.js:7124) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 34.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
34 tools are registered unconditionally · (1) 4 more only when options.includeGrowthTools holds (dist/http-server.js:7103) · (2) 5 more only when options.includeAdminAgentTaskTools holds (dist/http-server.js:7106) · (3) 2 more only when opts.includeGenericExecutor === false is false (dist/http-server.js:6448) · (4) 13 more only when options.includeContractsTools holds (dist/http-server.js:7109) · (5) 8 more only when options.includeApTools holds (dist/http-server.js:7112) · (6) 16 more only when options.includeDocGenTools holds (dist/http-server.js:7115) · (7) 12 more only when options.includePartiesTools holds (dist/http-server.js:7118) · (8) 8 more only when options.includeMasterRecordsTools holds (dist/http-server.js:7121) · (9) 6 more only when options.includeSubmissionsTools holds (dist/http-server.js:7124) — typically when a key or option is configured. All 108 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| talonic_extract | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| talonic_filter | no tags | |
| talonic_get_balance | no tags | |
| talonic_get_pricing | no tags | |
| talonic_get_usage | no tags | |
| talonic_get_document | no tags | |
| talonic_list_schemas | no tags | |
| talonic_save_schema | state-write | state-write: declares readOnlyHint: false |
| talonic_search | no tags | |
| talonic_request_upload | state-write | state-write: declares readOnlyHint: false |
| talonic_growth_funnel conditional (1) | no tags | |
| talonic_growth_funnels conditional (1) | no tags | |
| talonic_growth_traffic conditional (1) | no tags | |
| talonic_growth_tools_usage conditional (1) | no tags | |
| talonic_list_agent_tasks | no tags | |
| talonic_get_agent_task | no tags | |
| talonic_claim_agent_task | state-write | state-write: declares readOnlyHint: false |
| talonic_heartbeat_agent_task | state-write | state-write: declares readOnlyHint: false |
| talonic_submit_agent_task | state-write | state-write: declares readOnlyHint: false |
| talonic_admin_list_agent_tasks conditional (2) | no tags | |
| talonic_admin_get_agent_task conditional (2) | untrusted-input | untrusted-input: keyword "fetch" |
| talonic_admin_claim_agent_task conditional (2) | state-write | state-write: declares readOnlyHint: false |
| talonic_admin_heartbeat_agent_task conditional (2) | state-write | state-write: declares readOnlyHint: false |
| talonic_admin_submit_agent_task conditional (2) | state-write | state-write: declares readOnlyHint: false |
| talonic_list_decision_tasks | no tags | |
| talonic_claim_decision_task | no tags | |
| talonic_read_decision_package | no tags | |
| talonic_heartbeat_decision_task | no tags | |
| talonic_submit_decision_task | no tags | |
| talonic_release_decision_task | no tags | |
| talonic_fail_decision_task | no tags | |
| talonic_to_markdown | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| talonic_list_fields | no tags | |
| talonic_get_field | no tags | |
| talonic_field_values | no tags | |
| talonic_find_data | no tags | |
| talonic_list_agent_tools conditional (3) | no tags | |
| talonic_invoke_agent_tool conditional (3) | no tags | |
| talonic_list_specs | no tags | |
| talonic_get_spec | no tags | |
| talonic_run_spec | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| talonic_get_run | no tags | |
| talonic_get_run_results | no tags | |
| talonic_ask | state-write | state-write: declares readOnlyHint: false |
| talonic_get_answer | no tags | |
| talonic_contracts_register conditional (4) | no tags | |
| talonic_contracts_contract conditional (4) | no tags | |
| talonic_contracts_issues conditional (4) | no tags | |
| talonic_contracts_upcoming conditional (4) | no tags | |
| talonic_contracts_import_candidates conditional (4) | no tags | |
| talonic_contracts_import_status conditional (4) | no tags | |
| talonic_contracts_import conditional (4) | no tags | |
| talonic_contracts_update_document conditional (4) | no tags | |
| talonic_contracts_merge conditional (4) | no tags | |
| talonic_contracts_reread conditional (4) | no tags | |
| talonic_contracts_decide conditional (4) | no tags | |
| talonic_contracts_key_date conditional (4) | no tags | |
| talonic_contracts_set_term conditional (4) | no tags | |
| talonic_ap_overview conditional (5) | no tags | |
| talonic_ap_bills conditional (5) | no tags | |
| talonic_ap_issues conditional (5) | no tags | |
| talonic_ap_config conditional (5) | no tags | |
| talonic_ap_save_config conditional (5) | no tags | |
| talonic_ap_netsuite_preview conditional (5) | no tags | |
| talonic_ap_netsuite_post conditional (5) | no tags | |
| talonic_ap_netsuite_runs conditional (5) | no tags | |
| talonic_doc_gen_status conditional (6) | no tags | |
| talonic_doc_gen_issues conditional (6) | no tags | |
| talonic_doc_gen_templates conditional (6) | no tags | |
| talonic_doc_gen_update_template conditional (6) | no tags | |
| talonic_doc_gen_confirm_fields conditional (6) | no tags | |
| talonic_doc_gen_propose conditional (6) | no tags | |
| talonic_doc_gen_upload_template conditional (6) | no tags | |
| talonic_doc_gen_delete_template conditional (6) | no tags | |
| talonic_doc_gen_products conditional (6) | no tags | |
| talonic_doc_gen_rules conditional (6) | no tags | |
| talonic_doc_gen_profile conditional (6) | no tags | |
| talonic_doc_gen_draft conditional (6) | no tags | |
| talonic_doc_gen_generate conditional (6) | no tags | |
| talonic_doc_gen_jobs conditional (6) | no tags | |
| talonic_doc_gen_retry_pdf conditional (6) | no tags | |
| talonic_doc_gen_file conditional (6) | no tags | |
| talonic_parties_status conditional (7) | no tags | |
| talonic_parties_issues conditional (7) | no tags | |
| talonic_parties_contracts conditional (7) | no tags | |
| talonic_parties_contract conditional (7) | no tags | |
| talonic_parties_search conditional (7) | no tags | |
| talonic_parties_party conditional (7) | no tags | |
| talonic_parties_set_role conditional (7) | no tags | |
| talonic_parties_confirm conditional (7) | no tags | |
| talonic_parties_merge conditional (7) | no tags | |
| talonic_parties_read conditional (7) | no tags | |
| talonic_parties_members conditional (7) | no tags | |
| talonic_parties_group_companies conditional (7) | no tags | |
| talonic_master_records_config conditional (8) | no tags | |
| talonic_master_records_save_config conditional (8) | no tags | |
| talonic_master_records_run conditional (8) | no tags | |
| talonic_master_records_overview conditional (8) | no tags | |
| talonic_master_records_get_record conditional (8) | no tags | |
| talonic_master_records_decide conditional (8) | no tags | |
| talonic_master_records_changes conditional (8) | no tags | |
| talonic_master_records_crosswalk conditional (8) | no tags | |
| talonic_submissions_specs conditional (9) | no tags | |
| talonic_submissions_list conditional (9) | no tags | |
| talonic_submissions_issues conditional (9) | no tags | |
| talonic_submissions_process conditional (9) | no tags | |
| talonic_submissions_completeness conditional (9) | no tags | |
| talonic_submissions_export conditional (9) | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digestf0f481aa77a63f81
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.90. Pin a release below and the command asks for exactly that one.
0.1.90
14 Oct 2026
latestNo release note was published with this version.
0.1.89
12 Oct 2026
No release note was published with this version.
0.1.86
9 Oct 2026
No release note was published with this version.
0.1.85
8 Oct 2026
No release note was published with this version.
0.1.84
6 Oct 2026
No release note was published with this version.
0.1.83
6 Oct 2026
No release note was published with this version.
0.1.82
25 Sep 2026
No release note was published with this version.
0.1.79
22 Sep 2026
No release note was published with this version.
0.1.76
6 Sep 2026
No release note was published with this version.
0.1.75
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Talonic can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.